NeurIPS 2023 Papers

Browse

mini compact topic detail

SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models

Gacs-Korner Common Information Variational Autoencoder

Experimental Designs for Heteroskedastic Variance

Estimating Causal Effects Identifiable from a Combination of Observations and Experiments

Equal Opportunity of Coverage in Fair Regression

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs

Differentiable sorting for censored time-to-event data.

On the Role of Randomization in Adversarially Robust Classification

Polyhedron Attention Module: Learning Adaptive-order Interactions

On the Robustness of Removal-Based Feature Attributions

Equivariant Single View Pose Prediction Via Induced and Restriction Representations

Is RLHF More Difficult than Standard RL? A Theoretical Perspective

Multimodal Deep Learning Model Unveils Behavioral Dynamics of V1 Activity in Freely Moving Mice

Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features

A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis

P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting

Label Poisoning is All You Need

Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives

Equivariant Adaptation of Large Pretrained Models

Exploring Geometry of Blind Spots in Vision models

Are aligned neural networks adversarially aligned?

SaVeNet: A Scalable Vector Network for Enhanced Molecular Representation Learning

End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes

Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention

Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization

Relax, it doesn’t matter how you get there: A new self-supervised approach for multi-timescale behavior analysis

Spatial-frequency channels, shape bias, and adversarial robustness

$\varepsilon$-fractional core stability in Hedonic Games.

Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations

Language Model Alignment with Elastic Reset

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

Understanding Deep Gradient Leakage via Inversion Influence Functions

Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment

Joint Prompt Optimization of Stacked LLMs using Variational Inference

PROTES: Probabilistic Optimization with Tensor Sampling

A unified framework for information-theoretic generalization bounds

The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation

Variational Gaussian processes for linear inverse problems

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning

Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction

First Order Stochastic Optimization with Oblivious Noise

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels

Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts

Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms

Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model

Convex and Non-convex Optimization Under Generalized Smoothness

Reflexion: language agents with verbal reinforcement learning

Ordering-based Conditions for Global Convergence of Policy Gradient Methods

Topology-Aware Uncertainty for Image Segmentation

Fast and Simple Spectral Clustering in Theory and Practice

Information Geometry of the Retinal Representation Manifold

Smooth, exact rotational symmetrization for deep learning on point clouds

Convergence of Adam Under Relaxed Assumptions

Latent SDEs on Homogeneous Spaces

Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization

Bicriteria Approximation Algorithms for the Submodular Cover Problem

Neural Sampling in Hierarchical Exponential-family Energy-based Models

On Separate Normalization in Self-supervised Transformers

Tester-Learners for Halfspaces: Universal Algorithms

Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach

Online List Labeling with Predictions

Energy-based learning algorithms for analog computing: a comparative study

Outlier-Robust Wasserstein DRO

MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks

Conformal Prediction Sets for Ordinal Classification

Graph of Circuits with GNN for Exploring the Optimal Design Space

Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems

Online learning of long-range dependencies

ExPT: Synthetic Pretraining for Few-Shot Experimental Design

Incentivized Communication for Federated Bandits

Learning Provably Robust Estimators for Inverse Problems via Jittering

On the Exploitability of Instruction Tuning

Ensemble-based Deep Reinforcement Learning for Vehicle Routing Problems under Distribution Shift

Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows

Human spatiotemporal pattern learning as probabilistic program synthesis

Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement

Quantification of Uncertainty with Adversarial Models

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning

Correlation Aware Sparsified Mean Estimation Using Random Projection

Provably Efficient Offline Reinforcement Learning in Regular Decision Processes

SHAP-IQ: Unified Approximation of any-order Shapley Interactions

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings

Topological Obstructions and How to Avoid Them

On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks

Generalized test utilities for long-tail performance in extreme multi-label classification

Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent

What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models

Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images

Optimality of Message-Passing Architectures for Sparse Graphs

Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming

Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception

Accelerating Exploration with Unlabeled Prior Data

Accessing Higher Dimensions for Unsupervised Word Translation

D-CIPHER: Discovery of Closed-form Partial Differential Equations

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification

Reversible and irreversible bracket-based dynamics for deep graph neural networks

UP-NeRF: Unconstrained Pose Prior-Free Neural Radiance Field

Stable Vectorization of Multiparameter Persistent Homology using Signed Barcodes as Measures

Training on Foveated Images Improves Robustness to Adversarial Attacks

Towards Combinatorial Generalization for Catalysts: A Kohn-Sham Charge-Density Approach

Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation

A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs

Creating a Public Repository for Joining Private Data

Can semi-supervised learning use all the data effectively? A lower bound perspective

Learning Reliable Logical Rules with SATNet

A Unified Approach for Maximizing Continuous DR-submodular Functions

Hardware Resilience Properties of Text-Guided Image Classifiers

Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games

Direct Preference-based Policy Optimization without Reward Modeling

Faster Query Times for Fully Dynamic $k$-Center Clustering with Outliers

Physics-Informed Bayesian Optimization of Variational Quantum Circuits

Why Does Sharpness-Aware Minimization Generalize Better Than SGD?

Attention as Implicit Structural Inference

Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs

Transportability for Bandits with Data from Different Environments

FIRAL: An Active Learning Algorithm for Multinomial Logistic Regression

Conformal Meta-learners for Predictive Inference of Individual Treatment Effects

A Unified Model and Dimension for Interactive Estimation

Towards In-context Scene Understanding

Should Under-parameterized Student Networks Copy or Average Teacher Weights?

Memory Efficient Optimizers with 4-bit States

A Robust Exact Algorithm for the Euclidean Bipartite Matching Problem

Quantum speedups for stochastic optimization

Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization

Convergence Analysis of Sequential Federated Learning on Heterogeneous Data

Convergence of Alternating Gradient Descent for Matrix Factorization

Optimal Rates for Bandit Nonstochastic Control

Causal Effect Identification in Uncertain Causal Networks

Robust Bayesian Satisficing

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization

Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning

CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference

GLIME: General, Stable and Local LIME Explanation

SatLM: Satisfiability-Aided Language Models Using Declarative Prompting

Robust and Actively Secure Serverless Collaborative Learning

Learning to Influence Human Behavior with Offline Reinforcement Learning

MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates

Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image

Flow-Attention-based Spatio-Temporal Aggregation Network for 3D Mask Detection

Federated Linear Bandits with Finite Adversarial Actions

Recommender Systems with Generative Retrieval

Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions

Learning to Modulate pre-trained Models in RL

Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations

The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks

Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee

PDP: Parameter-free Differentiable Pruning is All You Need

StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation

Efficient Beam Tree Recursion

Projection-Free Online Convex Optimization via Efficient Newton Iterations

Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons

On the Size and Approximation Error of Distilled Datasets

Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments

Structured Neural Networks for Density Estimation and Causal Inference

Reusable Slotwise Mechanisms

Posterior Sampling for Competitive RL: Function Approximation and Partial Observation

A generative model of the hippocampal formation trained with theta driven local learning rules

The Bayesian Stability Zoo

Ignorance is Bliss: Robust Control via Information Gating

Double Gumbel Q-Learning

Optimistic Meta-Gradients

Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability

Learning Mixtures of Gaussians Using the DDPM Objective

Scalable Transformer for PDE Surrogate Modeling

Spatio-Angular Convolutions for Super-resolution in Diffusion MRI

A Privacy-Friendly Approach to Data Valuation

Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits

Pruning vs Quantization: Which is Better?

Common Ground in Cooperative Communication

Scalable Fair Influence Maximization

Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms

Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms

MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy

Reverse Engineering Self-Supervised Learning

Model-Free Reinforcement Learning with the Decision-Estimation Coefficient

Accelerating Molecular Graph Neural Networks via Knowledge Distillation

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

Partial Matrix Completion

Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees

Group Fairness in Peer Review

Improved Frequency Estimation Algorithms with and without Predictions

Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows

Frequency Domain-Based Dataset Distillation

Similarity-based cooperative equilibrium

Simplifying Neural Network Training Under Class Imbalance

Domain Agnostic Fourier Neural Operators

On the Role of Entanglement and Statistics in Learning

A Partially-Supervised Reinforcement Learning Framework for Visual Active Search

Robust Data Valuation with Weighted Banzhaf Values

Nonparametric Boundary Geometry in Physics Informed Deep Learning

Exact Verification of ReLU Neural Control Barrier Functions

Enhancing Robot Program Synthesis Through Environmental Context

Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks

BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization

Learning Shared Safety Constraints from Multi-task Demonstrations

Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity

Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization

NCDL: A Framework for Deep Learning on non-Cartesian Lattices

A Path to Simpler Models Starts With Noise

SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations

Batchnorm Allows Unsupervised Radial Attacks

A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions

Cognitive Model Discovery via Disentangled RNNs

Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning

Non-Convex Bilevel Optimization with Time-Varying Objective Functions

Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View

Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning

Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning

Implicit variance regularization in non-contrastive SSL

Pseudo-Likelihood Inference

Star-Shaped Denoising Diffusion Probabilistic Models

Hierarchical clustering with dot products recovers hidden tree structure

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

PromptIR: Prompting for All-in-One Image Restoration

Kernel-Based Tests for Likelihood-Free Hypothesis Testing

Learning DAGs from Data with Few Root Causes

Randomized and Deterministic Maximin-share Approximations for Fractionally Subadditive Valuations

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging

Implicit Regularization in Over-Parameterized Support Vector Machine

Auxiliary Losses for Learning Generalizable Concept-based Models

GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection

Grassmann Manifold Flows for Stable Shape Generation

Bayesian Optimisation of Functions on Graphs

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

Structured State Space Models for In-Context Reinforcement Learning

Normalizing flow neural networks by JKO scheme

On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models

Sample based Explanations via Generalized Representers

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples

Empowering Convolutional Neural Nets with MetaSin Activation

Bounded rationality in structured density estimation

Riemannian Laplace approximations for Bayesian neural networks

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

A Bayesian Approach To Analysing Training Data Attribution In Deep Learning

Human-Guided Complexity-Controlled Abstractions

Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation

Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability

Variational Annealing on Graphs for Combinatorial Optimization

EICIL: Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks

Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone

An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures

Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning

Exploiting hidden structures in non-convex games for convergence to Nash equilibrium

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

Diffusion Model for Graph Inverse Problems: Towards Effective Source Localization on Complex Networks

$p$-value Adjustment for Monotonous, Unbiased, and Fast Clustering Comparison

Inferring the Future by Imagining the Past

The Graph Pencil Method: Mapping Subgraph Densities to Stochastic Block Models

Improving Self-supervised Molecular Representation Learning using Persistent Homology

Utilitarian Algorithm Configuration

Beta Diffusion

Learning Transformer Programs

Simple and Controllable Music Generation

Mitigating the Effect of Incidental Correlations on Part-based Learning

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games

Learning to Discover Skills through Guidance

xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data

Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models

Risk-Averse Active Sensing for Timely Outcome Prediction under Cost Pressure

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

Accurate Interpolation for Scattered Data through Hierarchical Residual Refinement

Hybrid Policy Optimization from Imperfect Demonstrations

Optimal Preconditioning and Fisher Adaptive Langevin Sampling

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods

WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization

AMDP: An Adaptive Detection Procedure for False Discovery Rate Control in High-Dimensional Mediation Analysis

Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards

Human-Aligned Calibration for AI-Assisted Decision Making

Cross-Domain Policy Adaptation via Value-Guided Data Filtering

Fast Projected Newton-like Method for Precision Matrix Estimation under Total Positivity

Stable Nonconvex-Nonconcave Training via Linear Interpolation

FAST: a Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects Estimation

Near-optimal learning with average Hölder smoothness

Advancing Bayesian Optimization via Learning Correlated Latent Space

Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels

Generalized Information-theoretic Multi-view Clustering

A Definition of Continual Reinforcement Learning

LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion

DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views

Few-shot Generation via Recalling Brain-Inspired Episodic-Semantic Memory

Latent Space Translation via Semantic Alignment

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

Clifford Group Equivariant Neural Networks

NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA

Object-centric Learning with Cyclic Walks between Parts and Whole

Circuit as Set of Points

Energy Guided Diffusion for Generating Neurally Exciting Images

Fast Bellman Updates for Wasserstein Distributionally Robust MDPs

IBA: Towards Irreversible Backdoor Attacks in Federated Learning

SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations

Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data

Meta-learning families of plasticity rules in recurrent spiking networks using simulation-based inference

Certification of Distributional Individual Fairness

Attacks on Online Learners: a Teacher-Student Analysis

Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization

An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits

Use perturbations when learning from explanations

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Private estimation algorithms for stochastic block models and mixture models

Learning Cuts via Enumeration Oracles

Fair Canonical Correlation Analysis

Towards Test-Time Refusals via Concept Negation

On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

Dynamic Regret of Adversarial Linear Mixture MDPs

Conservative State Value Estimation for Offline Reinforcement Learning

FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations

On the Interplay between Social Welfare and Tractability of Equilibria

ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion

Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense

Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima

Streaming PCA for Markovian Data

Lookaround Optimizer: $k$ steps around, 1 step average

Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs

Fully Dynamic $k$-Clustering in $\tilde O(k)$ Update Time

Connecting Certified and Adversarial Training

Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing

Toward Understanding Generative Data Augmentation

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering

Provable Training for Graph Contrastive Learning

Learning Layer-wise Equivariances Automatically using Gradients

Decision Tree for Locally Private Estimation with Public Data

Equivariant flow matching

Implicit Manifold Gaussian Process Regression

ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

The Contextual Lasso: Sparse Linear Models via Deep Neural Networks

Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning

Deep Insights into Noisy Pseudo Labeling on Graph Data

Causal Interpretation of Self-Attention in Pre-Trained Transformers

Deep Recurrent Optimal Stopping

Stochastic Approximation Algorithms for Systems of Interacting Particles

Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination

Structured Voronoi Sampling

LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings

Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond

MMD-Fuse: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting

Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction

On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails

DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

Unified Segment-to-Segment Framework for Simultaneous Sequence Generation

Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models

Hybrid Search for Efficient Planning with Completeness Guarantees

SLaM: Student-Label Mixing for Distillation with Unlabeled Examples

Towards Robust and Expressive Whole-body Human Pose and Shape Estimation

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry

Fast Approximation of Similarity Graphs with Kernel Density Estimation

AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning

A Unified Framework for U-Net Design and Analysis

Policy Gradient for Rectangular Robust Markov Decision Processes

Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning

D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion

An Adaptive Algorithm for Learning with Unknown Distribution Drift

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach

Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond

TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

Knowledge Diffusion for Distillation

Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift

Regression with Cost-based Rejection

Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily

Automatic Integration for Spatiotemporal Neural Point Processes

Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation

Hierarchical Randomized Smoothing

Direct Training of SNN using Local Zeroth Order Method

Disentangling Voice and Content with Self-Supervision for Speaker Recognition

Understanding and Improving Ensemble Adversarial Defense

Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics

Theoretical and Practical Perspectives on what Influence Functions Do

Estimating the Rate-Distortion Function by Wasserstein Gradient Descent

Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context

TRIAGE: Characterizing and auditing training data for improved regression

Generalization in the Face of Adaptivity: A Bayesian Perspective

ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields

Efficiently incorporating quintuple interactions into geometric deep learning force fields

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data

Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation

Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory

MomentDiff: Generative Video Moment Retrieval from Random to Real

Temporal Dynamic Quantization for Diffusion Models

Self-Predictive Universal AI

Causal Component Analysis

Nonparametric Identifiability of Causal Representations from Unknown Interventions

CLadder: Assessing Causal Reasoning in Language Models

Improving neural network representations using human similarity judgments

AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation

NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics

Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning

Reinforcement Learning with Simple Sequence Priors

Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions

StoryBench: A Multifaceted Benchmark for Continuous Story Visualization

Robust Mean Estimation Without Moments for Symmetric Distributions

Federated Compositional Deep AUC Maximization

Window-Based Distribution Shift Detection for Deep Neural Networks

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

Bayesian Active Causal Discovery with Multi-Fidelity Experiments

CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss

Online PCA in Converging Self-consistent Field Equations

Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy

On Slicing Optimality for Mutual Information

k-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy

Information Maximization Perspective of Orthogonal Matching Pursuit with Applications to Explainable AI

Conditional Matrix Flows for Gaussian Graphical Models

Two-Stage Learning to Defer with Multiple Experts

Multiply Robust Federated Estimation of Targeted Average Treatment Effects

On the Variance, Admissibility, and Stability of Empirical Risk Minimization

To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task

Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width

Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture

Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness

Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context

Red Teaming Deep Neural Networks with Feature Synthesis Tools

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces

Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses

Agnostically Learning Single-Index Models using Omnipredictors

Combining Behaviors with the Successor Features Keyboard

Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation

Data Market Design through Deep Learning

Text Alignment Is An Efficient Unified Model for Massive NLP Tasks

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

f-Policy Gradients: A General Framework for Goal-Conditioned RL using f-Divergences

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering

A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning

Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances

Hierarchical VAEs provide a normative account of motion processing in the primate brain

Optimal testing using combined test statistics across independent studies

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models

Tracking Most Significant Shifts in Nonparametric Contextual Bandits

SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions

Precise asymptotic generalization for multiclass classification with overparameterized linear models

Fair Adaptive Experiments

Diverse Shape Completion via Style Modulated Generative Adversarial Networks

UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures

Understanding the detrimental class-level effects of data augmentation

Versatile Energy-Based Probabilistic Models for High Energy Physics

Compositional Generalization from First Principles

SpecTr: Fast Speculative Decoding via Optimal Transport

Fair, Polylog-Approximate Low-Cost Hierarchical Clustering

Minimax-Optimal Location Estimation

Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation

Projection-Free Methods for Solving Nonconvex-Concave Saddle Point Problems

A polar prediction model for learning to represent visual transformations

Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards

No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models

Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder

HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation

No-Regret Online Prediction with Strategic Experts

Uncovering motifs of concurrent signaling across multiple neuronal populations

ELDEN: Exploration via Local Dependencies

Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures

How to Scale Your EMA

Single-Pass Pivot Algorithm for Correlation Clustering. Keep it simple!

Model-free Posterior Sampling via Learning Rate Randomization

A Unified, Scalable Framework for Neural Population Decoding

A Trichotomy for Transductive Online Learning

Towards Automated Circuit Discovery for Mechanistic Interpretability

Generating Behaviorally Diverse Policies with Latent Diffusion Models

Distributed Personalized Empirical Risk Minimization

Structured Prediction with Stronger Consistency Guarantees

Feature Learning for Interpretable, Performant Decision Trees

Advice Querying under Budget Constraint for Online Algorithms

Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression

MIMEx: Intrinsic Rewards from Masked Input Modeling

Prioritizing Samples in Reinforcement Learning with Reducible Loss

Spatially Resolved Gene Expression Prediction from Histology Images via Bi-modal Contrastive Learning

Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts

Group Robust Classification Without Any Group Information

Egocentric Planning for Scalable Embodied Task Achievement

Lie Point Symmetry and Physics-Informed Networks

PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction

Derandomized novelty detection with FDR control via conformal e-values

Adversarial Learning for Feature Shift Detection and Correction

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

Rethinking Gauss-Newton for learning over-parameterized models

SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions

Compositional Sculpting of Iterative Generative Processes

High-Fidelity Audio Compression with Improved RVQGAN

A State Representation for Diminishing Rewards

Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier

Online POMDP Planning with Anytime Deterministic Guarantees

Residual Q-Learning: Offline and Online Policy Customization without Value

Near Optimal Reconstruction of Spherical Harmonic Expansions

Automated Classification of Model Errors on ImageNet

Towards robust and generalizable representations of extracellular data using contrastive learning

The Gain from Ordering in Online Learning

Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

MarioGPT: Open-Ended Text2Level Generation through Large Language Models

Distribution-Free Statistical Dispersion Control for Societal Applications

Small batch deep reinforcement learning

Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference

Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs

Detecting hidden confounding in observational data using multiple environments

Learning and processing the ordinal information of temporal sequences in recurrent neural circuits

Multi Time Scale World Models

Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization

Model-Free Active Exploration in Reinforcement Learning

Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes

Self-Supervised Reinforcement Learning that Transfers using Random Features

KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training

List and Certificate Complexities in Replicable Learning

Towards Unbounded Machine Unlearning

$p$-Poisson surface reconstruction in curl-free flow from point clouds

DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening

On the Convergence of CART under Sufficient Impurity Decrease Condition

FlowPG: Action-constrained Policy Gradient with Normalizing Flows

Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization

Variational Monte Carlo on a Budget — Fine-tuning pre-trained Neural Wavefunctions

Nearly Optimal Bounds for Cyclic Forgetting

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations

The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit

Doubly Robust Augmented Transfer for Meta-Reinforcement Learning

Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels

Anytime Model Selection in Linear Bandits

Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More

Learning Linear Causal Representations from Interventions under General Nonlinear Mixing

Towards Optimal Effective Resistance Estimation

Geometric Transformer with Interatomic Positional Encoding

Rotating Features for Object Discovery

Scaling MLPs: A Tale of Inductive Bias

Emergent and Predictable Memorization in Large Language Models

Strategic Behavior in Two-sided Matching Markets with Prediction-enhanced Preference-formation

Bayes beats Cross Validation: Efficient and Accurate Ridge Regression via Expectation Maximization

Counterfactual Evaluation of Peer-Review Assignment Policies

Emergent Communication for Rules Reasoning

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

On the Connection between Pre-training Data Diversity and Fine-tuning Robustness

Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach

The emergence of clusters in self-attention dynamics

An Inductive Bias for Tabular Deep Learning

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

CEIL: Generalized Contextual Imitation Learning

Training Transformers with 4-bit Integers

Estimating Propensity for Causality-based Recommendation without Exposure Data

Blockwise Parallel Transformers for Large Context Models

BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization

Matrix Compression via Randomized Low Rank and Low Precision Factorization

Adapting to Continuous Covariate Shift via Online Density Ratio Estimation

From Tempered to Benign Overfitting in ReLU Neural Networks

Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

Towards Self-Interpretable Graph-Level Anomaly Detection

Optimal Transport for Treatment Effect Estimation

Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment

VOCE: Variational Optimization with Conservative Estimation for Offline Safe Reinforcement Learning

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints

Function Space Bayesian Pseudocoreset for Bayesian Neural Networks

CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes

DesCo: Learning Object Recognition with Rich Language Descriptions

Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces

Unbiased learning of deep generative models with structured discrete representations

Geometry-Informed Neural Operator for Large-Scale 3D PDEs

Grounding Neural Inference with Satisfiability Modulo Theories

Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

Evolving Connectivity for Recurrent Spiking Neural Networks

Counterfactually Fair Representation

Emergent Communication in Interactive Sketch Question Answering

Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation

Identifiable Contrastive Learning with Automatic Feature Importance Discovery

Likelihood-Based Diffusion Language Models

PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning

Brant: Foundation Model for Intracranial Neural Signal

Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling

Neural-Logic Human-Object Interaction Detection

Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time

HIQL: Offline Goal-Conditioned RL with Latent States as Actions

Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise

Residual Alignment: Uncovering the Mechanisms of Residual Networks

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent

Binary Radiance Fields

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions

Statistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits

Compressed Video Prompt Tuning

On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy

Diversify Your Vision Datasets with Automatic Diffusion-based Augmentation

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement

No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning

Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks

Doubly-Robust Self-Training

AdaPlanner: Adaptive Planning from Feedback with Language Models

Zero-shot causal learning

DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models

Uniform Convergence with Square-Root Lipschitz Loss

Object-Centric Slot Diffusion

Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement

Curriculum Learning With Infant Egocentric Videos

Towards Optimal Caching and Model Selection for Large Model Inference

Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer

RETVec: Resilient and Efficient Text Vectorizer

On the Planning Abilities of Large Language Models - A Critical Investigation

Long-Term Fairness with Unknown Dynamics

A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games

Scaling Riemannian Diffusion Models

Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization

Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication

Diffusion Self-Guidance for Controllable Image Generation

Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data

Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives

Stability Guarantees for Feature Attributions with Multiplicative Smoothing

Arbitrarily Scalable Environment Generators via Neural Cellular Automata

TopoSRL: Topology preserving self-supervised Simplicial Representation Learning

Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

Characterizing the Impacts of Semi-supervised Learning for Weak Supervision

Maximum Average Randomly Sampled: A Scale Free and Non-parametric Algorithm for Stochastic Bandits

Physics-Driven ML-Based Modelling for Correcting Inverse Estimation

Simplicity Bias in 1-Hidden Layer Neural Networks

$S^3$: Increasing GPU Utilization during Generative Inference for Higher Throughput

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization

Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models

Class-Conditional Conformal Prediction with Many Classes

Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

Certified Minimax Unlearning with Generalization Rates and Deletion Capacity

Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?

UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene

On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

Practical Differentially Private Hyperparameter Tuning with Subsampling

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

High dimensional, tabular deep learning with an auxiliary knowledge graph

Not All Out-of-Distribution Data Are Harmful to Open-Set Active Learning

Error Bounds for Learning with Vector-Valued Random Features

Contextual Bandits and Imitation Learning with Preference-Based Active Queries

What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

PAC Learning Linear Thresholds from Label Proportions

Payoff-based Learning with Matrix Multiplicative Weights in Quantum Games

POMDP Planning for Object Search in Partially Unknown Environment

MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

A case for reframing automated medical image classification as segmentation

Inner Product-based Neural Network Similarity

Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?

Can Language Models Solve Graph Problems in Natural Language?

CLIP-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments

Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing

The Impact of Positional Encoding on Length Generalization in Transformers

Demystifying the Optimal Performance of Multi-Class Classification

Self-Chained Image-Language Model for Video Localization and Question Answering

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints

Finite Population Regression Adjustment and Non-asymptotic Guarantees for Treatment Effect Estimation

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling and Beyond

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks

New Bounds for Hyperparameter Tuning of Regression Problems Across Instances

A Long $N$-step Surrogate Stage Reward for Deep Reinforcement Learning

Language Models are Weak Learners

Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Federated Object Detection

PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model

Demystifying Oversmoothing in Attention-Based Graph Neural Networks

ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation

User-Level Differential Privacy With Few Examples Per User

Participatory Personalization in Classification

Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability

ChatGPT-Powered Hierarchical Comparisons for Image Classification

Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training

Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork

Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption

MIM4DD: Mutual Information Maximization for Dataset Distillation

Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization

Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking

Maximization of Average Precision for Deep Learning with Adversarial Ranking Robustness

A new perspective on building efficient and expressive 3D equivariant graph neural networks

CosNet: A Generalized Spectral Kernel Network

Concept Algebra for (Score-Based) Text-Controlled Generative Models

State-Action Similarity-Based Representations for Off-Policy Evaluation

Adaptive Linear Estimating Equations

Why think step by step? Reasoning emerges from the locality of experience

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

Bandit Task Assignment with Unknown Processing Time

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

Game Solving with Online Fine-Tuning

Recurrent Temporal Revision Graph Networks

Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning

Explain Any Concept: Segment Anything Meets Concept-Based Explanation

Depth-discriminative Metric Learning for Monocular 3D Object Detection

Connecting Pre-trained Language Model and Downstream Task via Properties of Representation

An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits

Score-based Source Separation with Applications to Digital Communication Signals

Generalized Belief Transport

Weakly Coupled Deep Q-Networks

Provable benefits of score matching

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation

Weitzman's Rule for Pandora's Box with Correlations

Learning Mask-aware CLIP Representations for Zero-Shot Segmentation

CoDrug: Conformal Drug Property Prediction with Density Estimation under Covariate Shift

Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion

Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability

EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model

Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion

Flow Matching for Scalable Simulation-Based Inference

Optimal and Fair Encouragement Policy Evaluation and Learning

Machine learning detects terminal singularities

Universality laws for Gaussian mixtures in generalized linear models

CoLLAT: On Adding Fine-grained Audio Understanding to Language Models using Token-Level Locked-Language Tuning

Large Language Models Are Zero-Shot Time Series Forecasters

Multi-task Representation Learning for Pure Exploration in Bilinear Bandits

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff

Causal Effect Regularization: Automated Detection and Removal of Spurious Correlations

A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time

Max-Sliced Mutual Information

Probabilistic Inference in Reinforcement Learning Done Right

Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies

Active Negative Loss Functions for Learning with Noisy Labels

Transformer-based Planning for Symbolic Regression

Reference-Based POMDPs

Neuro-symbolic Learning Yielding Logical Constraints

Efficient Learning of Linear Graph Neural Networks via Node Subsampling

Transformers learn to implement preconditioned gradient descent for in-context learning

Responsible AI (RAI) Games and Ensembles

GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds

Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt

Persuading Farsighted Receivers in MDPs: the Power of Honesty

An information-theoretic quantification of the content of communication between brain regions

Modulated Neural ODEs

CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion

Focused Transformer: Contrastive Training for Context Scaling

Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields

EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning

Bicriteria Multidimensional Mechanism Design with Side Information

PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

Scalarization for Multi-Task and Multi-Domain Learning at Scale

Paxion: Patching Action Knowledge in Video-Language Foundation Models

Parallel Submodular Function Minimization

Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization

ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding

Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models

Mass-Producing Failures of Multimodal Systems with Language Models

Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly

Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment

Policy Space Diversity for Non-Transitive Games

Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models

A Randomized Approach to Tight Privacy Accounting

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

Improving Adversarial Transferability via Intermediate-level Perturbation Decay

Sequential Predictive Two-Sample and Independence Testing

Retaining Beneficial Information from Detrimental Data for Neural Network Repair

Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells

Are Emergent Abilities of Large Language Models a Mirage?

SQ Lower Bounds for Learning Mixtures of Linear Classifiers

Sparse Modular Activation for Efficient Sequence Modeling

Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization

Cross-Scale MAE: A Tale of Multiscale Exploitation in Remote Sensing

Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders

Module-wise Adaptive Distillation for Multimodality Foundation Models

Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation

STREAMER: Streaming Representation Learning and Event Segmentation in a Hierarchical Manner

Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics

Personalized Dictionary Learning for Heterogeneous Datasets

Expert load matters: operating networks at high accuracy and low manual effort

Implicit Convolutional Kernels for Steerable CNNs

Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore

Multi-Agent Learning with Heterogeneous Linear Contextual Bandits

Probabilistic Exponential Integrators

Back-Modality: Leveraging Modal Transformation for Data Augmentation

Multi-Swap k-Means++

Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms

DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning

Neural Modulation for Flash Memory: An Unsupervised Learning Framework for Improved Reliability

ViSt3D: Video Stylization with 3D CNN

Iterative Reachability Estimation for Safe Reinforcement Learning

Evolving Standardization for Continual Domain Generalization over Temporal Drift

Efficient Neural Music Generation

Bounding training data reconstruction in DP-SGD

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

Sequential Memory with Temporal Predictive Coding

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers

Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation

Color Equivariant Convolutional Networks

Learning Efficient Surrogate Dynamic Models with Graph Spline Networks

Optimization and Bayes: A Trade-off for Overparameterized Neural Networks

A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning

Imitation Learning from Vague Feedback

Towards Efficient Image Compression Without Autoregressive Models

Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation

Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds

Robust Matrix Sensing in the Semi-Random Model

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Differentiable Random Partition Models

Three Iterations of (d − 1)-WL Test Distinguish Non Isometric Clouds of d-dimensional Points

SAMoSSA: Multivariate Singular Spectrum Analysis with Stochastic Autoregressive Noise

Birth of a Transformer: A Memory Viewpoint

Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths

Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering

On kernel-based statistical learning theory in the mean field limit

Adjustable Robust Reinforcement Learning for Online 3D Bin Packing

Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model

Fair Graph Distillation

Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?

Moral Responsibility for AI Systems

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

Sorting with Predictions

Direct Diffusion Bridge using Data Consistency for Inverse Problems

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization

No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions

Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictors

Sparse Parameterization for Epitomic Dataset Distillation

Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model

Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors

RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks

SALSA VERDE: a machine learning attack on LWE with sparse small secrets

Federated Learning with Bilateral Curation for Partially Class-Disjoint Data

On the Identifiability and Interpretability of Gaussian Process Models

Towards Efficient and Accurate Winograd Convolution via Full Quantization

Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination

AmadeusGPT: a natural language interface for interactive animal behavioral analysis

Sampling from Structured Log-Concave Distributions via a Soft-Threshold Dikin Walk

Efficient Exploration in Continuous-time Model-based Reinforcement Learning

On the Power of SVD in the Stochastic Block Model

A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints

A Fractional Graph Laplacian Approach to Oversmoothing

Learning Regularized Monotone Graphon Mean-Field Games

Learning From Biased Soft Labels

Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language.

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

Noether Embedding: Efficient Learning of Temporal Regularities

An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

The Tunnel Effect: Building Data Representations in Deep Neural Networks

Structure Learning with Adaptive Random Neighborhood Informed MCMC

FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models

Deep Fractional Fourier Transform

Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do

Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions

Learning Dictionary for Visual Attention

Optimistic Active Exploration of Dynamical Systems

Label Correction of Crowdsourced Noisy Annotations with an Instance-Dependent Noise Transition Model

Cookie Consent Has Disparate Impact on Estimation Accuracy

Learning Large-scale Neural Fields via Context Pruned Meta-Learning

Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression

Wasserstein distributional robustness of neural networks

Recurrent Hypernetworks are Surprisingly Strong in Meta-RL

Faster Margin Maximization Rates for Generic Optimization Methods

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design

Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity

Outlier-Robust Gromov-Wasserstein for Graph Data

FairLISA: Fair User Modeling with Limited Sensitive Attributes Information

Reusing Pretrained Models by Multi-linear Operators for Efficient Training

Variational Weighting for Kernel Density Ratios

Taming Local Effects in Graph-based Spatiotemporal Forecasting

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

A Bayesian Take on Gaussian Process Networks

Granger Components Analysis: Unsupervised learning of latent temporal dependencies

Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment

MADG: Margin-based Adversarial Learning for Domain Generalization

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning

ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training

MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation

Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds

Characterization of Overfitting in Robust Multiclass Classification

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

Leveraging sparse and shared feature activations for disentangled representation learning

Entropy-based Training Methods for Scalable Neural Implicit Samplers

Implicit Contrastive Representation Learning with Guided Stop-gradient

A Robust and Opponent-Aware League Training Method for StarCraft II

Score-based Generative Models with Lévy Processes

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability

Balancing Risk and Reward: A Batched-Bandit Strategy for Automated Phased Release

Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models

Corruption-Robust Offline Reinforcement Learning with General Function Approximation

Gaussian Membership Inference Privacy

Coherent Soft Imitation Learning

An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint

Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models

Towards a Unified Framework of Contrastive Learning for Disentangled Representations

A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications

Convolution Monge Mapping Normalization for learning on sleep data

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Triangulation Residual Loss for Data-efficient 3D Pose Estimation

Cross-modal Active Complementary Learning with Self-refining Correspondence

Private Distribution Learning with Public Data: The View from Sample Compression

Hierarchical Multi-Agent Skill Discovery

Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage

Adaptive Online Replanning with Diffusion Models

Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

Failure-Aware Gaussian Process Optimization with Regret Bounds

Causal normalizing flows: from theory to practice

Multi-Agent First Order Constrained Optimization in Policy Space

Active Bipartite Ranking

Enhancing Adversarial Robustness via Score-Based Optimization

The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning

Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning

Mask Propagation for Efficient Video Semantic Segmentation

Fantastic Robustness Measures: The Secrets of Robust Generalization

Two Heads are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning

Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation

Distributional Pareto-Optimal Multi-Objective Reinforcement Learning

Reliable Off-Policy Learning for Dosage Combinations

Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces

Diffusion Representation for Asymmetric Kernels via Magnetic Transform

Context Shift Reduction for Offline Meta-Reinforcement Learning

Add and Thin: Diffusion for Temporal Point Processes

On quantum backpropagation, information reuse, and cheating measurement collapse

Optimal approximation using complex-valued neural networks

Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization

MMGP: a Mesh Morphing Gaussian Process-based machine learning method for regression of physical problems under nonparametrized geometrical variability

InstanT: Semi-supervised Learning with Instance-dependent Thresholds

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents

Mode Connectivity in Auction Design

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning

PPi: Pretraining Brain Signal Model for Patient-independent Seizure Detection

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

A General Framework for Equivariant Neural Networks on Reductive Lie Groups

Nearest Neighbour with Bandit Feedback

Curvature Filtrations for Graph Generative Model Evaluation

Adversarial Attacks on Online Learning to Rank with Click Feedback

Bayesian nonparametric (non-)renewal processes for analyzing neural spike train variability

L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference

Volume Feature Rendering for Fast Neural Radiance Field Reconstruction

FedL2P: Federated Learning to Personalize

Continuous Parametric Optical Flow

Extremal Domain Translation with Neural Optimal Transport

A Guide Through the Zoo of Biased SGD

Nearly Tight Bounds For Differentially Private Multiway Cut

CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches

Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression

How do Minimum-Norm Shallow Denoisers Look in Function Space?

Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions

On the Minimax Regret for Online Learning with Feedback Graphs

Optimal cross-learning for contextual bandits with unknown context distributions

GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising

Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing

Approximate inference of marginals using the IBIA framework

A Unified Framework for Rank-based Loss Minimization

On Evaluating Adversarial Robustness of Large Vision-Language Models

GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence

Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

Combating Representation Learning Disparity with Geometric Harmonization

HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

Rigorous Runtime Analysis of MOEA/D for Solving Multi-Objective Minimum Weight Base Problems

Learning Sample Difficulty from Pre-trained Models for Reliable Prediction

Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification

Computational Guarantees for Doubly Entropic Wasserstein Barycenters

Tailoring Self-Attention for Graph via Rooted Subtrees

Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning

Vocabulary-free Image Classification

Boosting Verification of Deep Reinforcement Learning via Piece-Wise Linear Decision Neural Networks

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Operation-Level Early Stopping for Robustifying Differentiable NAS

Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?

Neural Processes with Stability

Minimax Risks and Optimal Procedures for Estimation under Functional Local Differential Privacy

DeepPCR: Parallelizing Sequential Operations in Neural Networks

Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents

Joint Training of Deep Ensembles Fails Due to Learner Collusion

Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks

How to Turn Your Knowledge Graph Embeddings into Generative Models

Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models

Delegated Classification

Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions

Learning Invariant Representations of Graph Neural Networks via Cluster Generalization

Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy

Zero-sum Polymatrix Markov Games: Equilibrium Collapse and Efficient Computation of Nash Equilibria

SoTTA: Robust Test-Time Adaptation on Noisy Data Streams

Limits, approximation and size transferability for GNNs on sparse graphs via graphops

Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints

Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion

Facing Off World Model Backbones: RNNs, Transformers, and S4

Homotopy-based training of NeuralODEs for accurate dynamics discovery

Combinatorial Optimization with Policy Adaptation using Latent Space Search

Quantum Bayesian Optimization

Assumption violations in causal discovery and the robustness of score matching

Minimum Description Length and Generalization Guarantees for Representation Learning

Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion

Batch Bayesian Optimization For Replicable Experimental Design

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models

Diffused Task-Agnostic Milestone Planner

PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification

Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds

ODE-based Recurrent Model-free Reinforcement Learning for POMDPs

LEACE: Perfect linear concept erasure in closed form

Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP

Efficient Hyper-parameter Optimization with Cubic Regularization

Effective Targeted Attacks for Adversarial Self-Supervised Learning

Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks

Debiased and Denoised Entity Recognition from Distant Supervision

Schema-learning and rebinding as mechanisms of in-context learning and emergence

State Sequences Prediction via Fourier Transform for Representation Learning

Analysis of Variance of Multiple Causal Networks

Undirected Probabilistic Model for Tensor Decomposition

Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes

LICO: Explainable Models with Language-Image COnsistency

Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks

Active Learning-Based Species Range Estimation

Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes

Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension

Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach

A Computationally Efficient Sparsified Online Newton Method

Multi-Object Representation Learning via Feature Connectivity and Object-Centric Regularization

Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes

Efficient Subgame Refinement for Extensive-form Games

Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations

Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective

Contextually Affinitive Neighborhood Refinery for Deep Clustering

A Dynamical System View of Langevin-Based Non-Convex Sampling

Extracting Reward Functions from Diffusion Models

Riemannian stochastic optimization methods avoid strict saddle points

Rewiring Neurons in Non-Stationary Environments

DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning

Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss

Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards

Particle-based Variational Inference with Generalized Wasserstein Gradient Flow

Soft-Unification in Deep Probabilistic Logic

Robust covariance estimation with missing values and cell-wise contamination

Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters

Investigating how ReLU-networks encode symmetries

Enhancing Minority Classes by Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification

Activity Grammars for Temporal Action Segmentation

Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion

Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator

DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels

Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory

Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition

On the Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis

An active learning framework for multi-group mean estimation

From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models

Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach

Unsupervised Image Denoising with Score Function

Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks

Optimal Transport Model Distributional Robustness

WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding

On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds

Incomplete Multimodality-Diffused Emotion Recognition

Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models

Toolformer: Language Models Can Teach Themselves to Use Tools

Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

Sample-efficient Multi-objective Molecular Optimization with GFlowNets

Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels

Flat Seeking Bayesian Neural Networks

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models

Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model for Image Editing

Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL

Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection

Nonparametric Teaching for Multiple Learners

A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space

Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm

Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations

REFINE: A Fine-Grained Medication Recommendation System Using Deep Learning and Personalized Drug Interaction Modeling

MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers

Unsupervised Behavior Extraction via Random Intent Priors

Towards Accelerated Model Training via Bayesian Data Selection

Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

Mutual Information Regularized Offline Reinforcement Learning

The Exact Sample Complexity Gain from Invariances for Kernel Regression

Exploiting Contextual Objects and Relations for 3D Visual Grounding

Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity

Zero-Regret Performative Prediction Under Inequality Constraints

Calibration by Distribution Matching: Trainable Kernel Calibration Metrics

Partial Label Learning with Dissimilarity Propagation guided Candidate Label Shrinkage

Bandit Social Learning under Myopic Behavior

An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation

Diversify \& Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement

Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem

Compositional Foundation Models for Hierarchical Planning

NPCL: Neural Processes for Uncertainty-Aware Continual Learning

Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization

ARTree: A Deep Autoregressive Model for Phylogenetic Inference

Graph Denoising Diffusion for Inverse Protein Folding

Visual Instruction Inversion: Image Editing via Image Prompting

DiViNeT: 3D Reconstruction from Disparate Views using Neural Template Regularization

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

Weakly Supervised 3D Open-vocabulary Segmentation

Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints

Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis

A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization

Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition

On Differentially Private Sampling from Gaussian and Product Distributions

On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm

LightSpeed: Light and Fast Neural Light Fields on Mobile Devices

Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning

Neural Oscillators are Universal

Online Corrupted User Detection and Regret Minimization

On the Gini-impurity Preservation For Privacy Random Forests

On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions

Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations

Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks

Adaptive Test-Time Personalization for Federated Learning

Errors-in-variables Fr\'echet Regression with Low-rank Covariate Approximation

Federated Conditional Stochastic Optimization

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts

Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration

Gaussian Mixture Solvers for Diffusion Models

Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping

Hyperbolic VAE via Latent Gaussian Distributions

Efficient Low-rank Backpropagation for Vision Transformer Adaptation

Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm

Static and Sequential Malicious Attacks in the Context of Selective Forgetting

Online Clustering of Bandits with Misspecified User Models

The probability flow ODE is provably fast

On Calibrating Diffusion Probabilistic Models

Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions

Statistical Insights into HSIC in High Dimensions

Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning

Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

Restart Sampling for Improving Generative Processes

Geometry-Aware Adaptation for Pretrained Models

Incentives in Private Collaborative Machine Learning

Bayesian Optimization with Cost-varying Variable Subsets

Conditional Score Guidance for Text-Driven Image-to-Image Translation

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

What Makes Good Examples for Visual In-Context Learning?

Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration

D-Separation for Causal Self-Explanation

Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?

Perceptual Kalman Filters: Online State Estimation under a Perfect Perceptual-Quality Constraint

DSR: Dynamical Surface Representation as Implicit Neural Networks for Protein

Two-Stage Predict+Optimize for MILPs with Unknown Parameters in Constraints

Achieving Cross Modal Generalization with Multimodal Unified Representation

Generator Identification for Linear SDEs with Additive and Multiplicative Noise

On the Overlooked Structure of Stochastic Gradients

Private Everlasting Prediction

Hierarchical Gaussian Mixture based Task Generative Model for Robust Meta-Learning

Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models

In-Context Learning Unlocked for Diffusion Models

MGDD: A Meta Generator for Fast Dataset Distillation

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification

Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction

A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy

$L_2$-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting

Federated Spectral Clustering via Secure Similarity Reconstruction

Neural Graph Generation from Graph Statistics

Model-Based Control with Sparse Neural Dynamics

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training

Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization

ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

Newton–Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems

Tuning Multi-mode Token-level Prompt Alignment across Modalities

Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies

S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions

Text Promptable Surgical Instrument Segmentation with Vision-Language Models

Towards A Richer 2D Understanding of Hands at Scale

A Finite-Particle Convergence Rate for Stein Variational Gradient Descent

Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning

A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective

Feature Adaptation for Sparse Linear Regression

Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes

Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method

Efficient Testable Learning of Halfspaces with Adversarial Label Noise

Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications

Stable and low-precision training for large-scale vision-language models

Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior

Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models

TabMT: Generating tabular data with masked transformers

Tools for Verifying Neural Models' Training Data

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks

Clustering the Sketch: Dynamic Compression for Embedding Tables

Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training

Finite-Time Logarithmic Bayes Regret Upper Bounds

Adversarial Resilience in Sequential Prediction via Abstention

Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge

Balancing memorization and generalization in RNNs for high performance brain-machine Interfaces

Understanding and Mitigating Copying in Diffusion Models

Bootstrapping Vision-Language Learning with Decoupled Language Pre-training

On Generalization Bounds for Projective Clustering

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval

QuIP: 2-Bit Quantization of Large Language Models With Guarantees

Approximately Equivariant Graph Networks

GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels

Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data

Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks

Where Did I Come From? Origin Attribution of AI-Generated Images

Your representations are in the network: composable and parallel adaptation for large scale models

Faster Relative Entropy Coding with Greedy Rejection Coding

Visual Instruction Tuning

Aiming towards the minimizers: fast convergence of SGD for overparametrized problems

Near-Optimal $k$-Clustering in the Sliding Window Model

Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors

Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits

Order Matters in the Presence of Dataset Imbalance for Multilingual Learning

Invariant Anomaly Detection under Distribution Shifts: A Causal Perspective

InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion

The Crucial Role of Normalization in Sharpness-Aware Minimization

Causal Imitability Under Context-Specific Independence Relations

Identifiability Guarantees for Causal Disentanglement from Soft Interventions

Anonymous and Copy-Robust Delegations for Liquid Democracy

Boosting with Tempered Exponential Measures

TART: A plug-and-play Transformer module for task-agnostic reasoning

SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement

Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought

Distribution Learnability and Robustness

Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms

Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond

GloptiNets: Scalable Non-Convex Optimization with Certificates

Time Series as Images: Vision Transformer for Irregularly Sampled Time Series

CELLE-2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer

Explaining Predictive Uncertainty with Information Theoretic Shapley Values

The Behavior and Convergence of Local Bayesian Optimization

The Transient Nature of Emergent In-Context Learning in Transformers

Im-Promptu: In-Context Composition from Image Prompts

Scalable Membership Inference Attacks via Quantile Regression

Augmenting Language Models with Long-Term Memory

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

Information-guided Planning: An Online Approach for Partially Observable Problems

Energy Discrepancies: A Score-Independent Loss for Energy-Based Models

Fast Optimal Locally Private Mean Estimation via Random Projections

Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds

On the impact of activation and normalization in obtaining isometric embeddings at initialization

Zero-One Laws of Graph Neural Networks

Deep Stochastic Processes via Functional Markov Transition Operators

Computing a human-like reaction time metric from stable recurrent vision models

What can a Single Attention Layer Learn? A Study Through the Random Features Lens

Active representation learning for general task space with applications in robotics

Analyzing Vision Transformers for Image Classification in Class Embedding Space

Regularity as Intrinsic Reward for Free Play

Differentially Private Approximate Near Neighbor Counting in High Dimensions

Adaptive Algorithms for Relaxed Pareto Set Identification

Fitting trees to $\ell_1$-hyperbolic distances

Formalizing locality for normative synaptic plasticity models

Thin and deep Gaussian processes

Tempo Adaptation in Non-stationary Reinforcement Learning

Reconciling Competing Sampling Strategies of Network Embedding

Convergence of Actor-Critic with Multi-Layer Neural Networks

An Efficient Doubly-Robust Test for the Kernel Treatment Effect

Incentivizing Honesty among Competitors in Collaborative Learning and Optimization

From Trainable Negative Depth to Edge Heterophily in Graphs

Siamese Masked Autoencoders

PoET: A generative model of protein families as sequences-of-sequences

Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model

ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image

A Unified Fast Gradient Clipping Framework for DP-SGD

LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer

Continual Learning for Instruction Following from Realtime Feedback

Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions

Hyper-HMM: aligning human brains and semantic features in a common latent event space

Learning better with Dale’s Law: A Spectral Perspective

Long Sequence Hopfield Memory

Minimum norm interpolation by perceptra: Explicit regularization and implicit bias

Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Unified Lower Bounds for Interactive High-dimensional Estimation under Information Constraints

On the Robustness of Mechanism Design under Total Variation Distance

Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control

Asynchronous Proportional Response Dynamics: Convergence in Markets with Adversarial Scheduling

Learning via Wasserstein-Based High Probability Generalisation Bounds

Swarm Reinforcement Learning for Adaptive Mesh Refinement

Taking the neural sampling code very seriously: A data-driven approach for evaluating generative models of the visual system

Online Pricing for Multi-User Multi-Item Markets

Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs

Systematic Visual Reasoning through Object-Centric Relational Abstraction

On the Statistical Consistency of Risk-Sensitive Bayesian Decision-Making

$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

Break It Down: Evidence for Structural Compositionality in Neural Networks

Latent Diffusion for Language Generation

Causal Fairness for Outcome Control

Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation

Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning

Unsupervised Learning for Solving the Travelling Salesman Problem

PlanE: Representation Learning over Planar Graphs

LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference

Collapsed Inference for Bayesian Deep Learning

RegBN: Batch Normalization of Multimodal Data with Regularization

Policy Optimization for Continuous Reinforcement Learning

Video-Mined Task Graphs for Keystep Recognition in Instructional Videos

Algorithm Selection for Deep Active Learning with Imbalanced Datasets

Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent

Loss Dynamics of Temporal Difference Reinforcement Learning

Minimum-Risk Recalibration of Classifiers

When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability

Active Observing in Continuous-time Control

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

Scaling Open-Vocabulary Object Detection

Neural Image Compression: Generalization, Robustness, and Spectral Biases

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

How Does Adaptive Optimization Impact Local Neural Network Geometry?

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

Streaming Algorithms and Lower Bounds for Estimating Correlation Clustering Cost

Gaussian Differential Privacy on Riemannian Manifolds

Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems

Auditing for Human Expertise

Norm-based Generalization Bounds for Sparse Neural Networks

Replicable Reinforcement Learning

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

Stability of Random Forests and Coverage of Random-Forest Prediction Intervals

CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions

Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First

On the Importance of Exploration for Generalization in Reinforcement Learning

3D-LLM: Injecting the 3D World into Large Language Models

A Unified Approach to Count-Based Weakly Supervised Learning

On Single-Index Models beyond Gaussian Data

Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions

Accelerating Motion Planning via Optimal Transport

A General Framework for Robust G-Invariance in G-Equivariant Networks

Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars

Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction

EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding

Distributionally Robust Linear Quadratic Control

Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Tree Variational Autoencoders

FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow

EgoEnv: Human-centric environment representations from egocentric video

Debiasing Conditional Stochastic Optimization

A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning

Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training

Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing

On Computing Pairwise Statistics with Local Differential Privacy

Brain encoding models based on multimodal transformers can transfer across language and vision

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

Honesty Is the Best Policy: Defining and Mitigating AI Deception

Unbalanced Low-rank Optimal Transport Solvers

Auditing Fairness by Betting

Learning from Active Human Involvement through Proxy Value Propagation

Towards Last-layer Retraining for Group Robustness with Fewer Annotations

Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick

Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning

Meet in the Middle: A New Pre-training Paradigm

Adversarial Examples Are Not Real Features

Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

A graphon-signal analysis of graph neural networks

Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision

Generative Neural Fields by Mixtures of Neural Implicit Functions

DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization

Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding

SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network

On the Importance of Feature Separability in Predicting Out-Of-Distribution Error

Monte Carlo Tree Search with Boltzmann Exploration

CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

Supply-Side Equilibria in Recommender Systems

PETAL: Physics Emulation Through Averaged Linearizations for Solving Inverse Problems

Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs

Differentiable Clustering with Perturbed Spanning Forests

Alternating Updates for Efficient Transformers

Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition

On the Exploration of Local Significant Differences For Two-Sample Test

Meta-Learning with Neural Bandit Scheduler

Learning Causal Models under Independent Changes

Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

Pengi: An Audio Language Model for Audio Tasks

Beyond MLE: Convex Learning for Text Generation

Online Control for Meta-optimization

Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections

Moment Matching Denoising Gibbs Sampling

Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression

Conditional score-based diffusion models for Bayesian inference in infinite dimensions

Topological Parallax: A Geometric Specification for Deep Perception Models

TIES-Merging: Resolving Interference When Merging Models

Joint processing of linguistic properties in brains and language models

Self-Correcting Bayesian Optimization through Bayesian Active Learning

Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions

GEQ: Gaussian Kernel Inspired Equilibrium Models

Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents

$SE(3)$ Equivariant Convolution and Transformer in Ray Space

Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization

Creating Multi-Level Skill Hierarchies in Reinforcement Learning

Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow

Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition

Speculative Decoding with Big Little Decoder

ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation

Stein $\Pi$-Importance Sampling

Unexpected Improvements to Expected Improvement for Bayesian Optimization

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

A Unified Detection Framework for Inference-Stage Backdoor Defenses

Finding Local Minima Efficiently in Decentralized Optimization

Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?

Jigsaw: Learning to Assemble Multiple Fractured Objects

Sparsity-Preserving Differentially Private Training of Large Embedding Models

On the choice of Perception Loss Function for Learned Video Compression

PrObeD: Proactive Object Detection Wrapper

Refined Mechanism Design for Approximately Structured Priors via Active Regression

CAT-Walk: Inductive Hypergraph Learning via Set Walks

A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

Block Coordinate Plug-and-Play Methods for Blind Inverse Problems

Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making

Self-Consistent Velocity Matching of Probability Flows

An Inverse Scaling Law for CLIP Training

Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb

Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

On Proper Learnability between Average- and Worst-case Robustness

Should I Stop or Should I Go: Early Stopping with Heterogeneous Populations

On the Learnability of Multilabel Ranking

Score-based Generative Modeling through Stochastic Evolution Equations in Hilbert Spaces

Global Identifiability of $\ell_1$-based Dictionary Learning via Matrix Volume Optimization

Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations

Learning a 1-layer conditional generative model in total variation

TaskMet: Task-driven Metric Learning for Model Learning

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

Kissing to Find a Match: Efficient Low-Rank Permutation Representation

Differentially Private Image Classification by Learning Priors from Random Processes

Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework

CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation

Anytime-Competitive Reinforcement Learning with Policy Prior

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards

Revisiting Area Convexity: Faster Box-Simplex Games and Spectrahedral Generalizations

Exponential Lower Bounds for Fictitious Play in Potential Games

NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs

NeRF Revisited: Fixing Quadrature Instability in Volume Rendering

Directed Cyclic Graph for Causal Discovery from Multivariate Functional Data

First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities

Data-Informed Geometric Space Selection

PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks

Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation

Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models

Budgeting Counterfactual for Offline RL

T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization

Towards Free Data Selection with General-Purpose Models

Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

Provably (More) Sample-Efficient Offline RL with Options

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

Survival Permanental Processes for Survival Analysis with Time-Varying Covariates

Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems

Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes

Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning

Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network

Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback

Maximum State Entropy Exploration using Predecessor and Successor Representations

E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning

Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning

GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks

Convolutional State Space Models for Long-Range Spatiotemporal Modeling

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos

Is Learning in Games Good for the Learners?

Effective Robustness against Natural Distribution Shifts for Models with Different Training Data

Content-based Unrestricted Adversarial Attack

Adapting Fairness Interventions to Missing Values

Intriguing Properties of Quantization at Scale

ReSync: Riemannian Subgradient-based Robust Rotation Synchronization

Squared Neural Families: A New Class of Tractable Density Models

Towards Symmetry-Aware Generation of Periodic Materials

GraphMP: Graph Neural Network-based Motion Planning with Efficient Graph Search

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting

Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation

Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects

A General Theory of Correct, Incorrect, and Extrinsic Equivariance

Multi-Fidelity Multi-Armed Bandits Revisited

Rethinking Conditional Diffusion Sampling with Progressive Guidance

Deep Non-line-of-sight Imaging from Under-scanning Measurements

Model Shapley: Equitable Model Valuation with Black-box Access

Black-box Backdoor Defense via Zero-shot Image Purification

Many-body Approximation for Non-negative Tensors

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

Preconditioning Matters: Fast Global Convergence of Non-convex Matrix Factorization via Scaled Gradient Descent

Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis

Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models

Invariant Learning via Probability of Sufficient and Necessary Causes

Fractal Landscapes in Policy Optimization

Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Geometric Analysis of Matrix Sensing over Graphs

On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes

HASSOD: Hierarchical Adaptive Self-Supervised Object Detection

Byzantine-Tolerant Methods for Distributed Variational Inequalities

Practical Contextual Bandits with Feedback Graphs

Robust Learning for Smoothed Online Convex Optimization with Feedback Delay

Disentanglement via Latent Quantization

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

Smoothed Analysis of Sequential Probability Assignment

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders

Causal discovery from observational and interventional data across multiple environments

Neural Lyapunov Control for Discrete-Time Systems

Dream the Impossible: Outlier Imagination with Diffusion Models

Neural Algorithmic Reasoning Without Intermediate Supervision

Energy-Efficient Scheduling with Predictions

DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics

Does Visual Pretraining Help End-to-End Reasoning?

CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

AutoGO: Automated Computation Graph Optimization for Neural Network Evolution

Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation

Time-uniform confidence bands for the CDF under nonstationarity

On the spectral bias of two-layer linear networks

Learning to Configure Separators in Branch-and-Cut

Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples

Provable convergence guarantees for black-box variational inference

VaRT: Variational Regression Trees

Unlimiformer: Long-Range Transformers with Unlimited Length Input

Inverse Reinforcement Learning with the Average Reward Criterion

On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence

Asymmetric Certified Robustness via Feature-Convex Neural Networks

Learning Exponential Families from Truncated Samples

Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Geodesic Multi-Modal Mixup for Robust Fine-Tuning

Conditional independence testing under misspecified inductive biases

What’s Left? Concept Grounding with Logic-Enhanced Foundation Models

Revisiting the Minimalist Approach to Offline Reinforcement Learning

Simultaneous embedding of multiple attractor manifolds in a recurrent neural network using constrained gradient optimization

Coupled Reconstruction of Cortical Surfaces by Diffeomorphic Mesh Deformation

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel

Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling

A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception

Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

Fair Allocation of Indivisible Chores: Beyond Additive Costs

Supported Value Regularization for Offline Reinforcement Learning

Sample Complexity of Forecast Aggregation

Learning Functional Transduction

Label-Only Model Inversion Attacks via Knowledge Transfer

PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks

Random Cuts are Optimal for Explainable k-Medians

FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation

Fine-grained Expressivity of Graph Neural Networks

Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling

Data Minimization at Inference Time

Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods

Near-Linear Time Algorithm for the Chamfer Distance

Language Model Tokenizers Introduce Unfairness Between Languages

History Filtering in Imperfect Information Games: Algorithms and Complexity

Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions

Fast Trainable Projection for Robust Fine-tuning

MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation

Entropic Neural Optimal Transport via Diffusion Processes

Semi-Supervised Domain Generalization with Known and Unknown Classes

Representation Learning via Consistent Assignment of Views over Random Partitions

Test-time Training for Matching-based Video Object Segmentation

Data Augmentations for Improved (Large) Language Model Generalization

Revisiting Implicit Differentiation for Learning Problems in Optimal Control

Learning Invariant Molecular Representation in Latent Discrete Space

High-dimensional Asymptotics of Denoising Autoencoders

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

3D molecule generation by denoising voxel grids

ProPILE: Probing Privacy Leakage in Large Language Models

Described Object Detection: Liberating Object Detection with Flexible Expressions

Kernelized Cumulants: Beyond Kernel Mean Embeddings

Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution

Learning from Visual Observation via Offline Pretrained State-to-Go Transformer

DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing

Inserting Anybody in Diffusion Models via Celeb Basis

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

DreamHuman: Animatable 3D Avatars from Text

Trade-off Between Efficiency and Consistency for Removal-based Explanations

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Fairness Aware Counterfactuals for Subgroups

SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement

New Complexity-Theoretic Frontiers of Tractability for Neural Network Training

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

Covariance-adaptive best arm identification

Metis: Understanding and Enhancing In-Network Regular Expressions

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection

Fed-CO$_{2}$: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning

SOAR: Improved Indexing for Approximate Nearest Neighbor Search

CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion

Fast Model DeBias with Machine Unlearning

“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization

Hypervolume Maximization: A Geometric View of Pareto Set Learning

RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy

Norm-guided latent space exploration for text-to-image generation

On skip connections and normalisation layers in deep optimisation

Language Is Not All You Need: Aligning Perception with Language Models

Robust Knowledge Transfer in Tiered Reinforcement Learning

Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks

On the Pareto Front of Multilingual Neural Machine Translation

DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field

TexQ: Zero-shot Network Quantization with Texture Feature Distribution Calibration

MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory

Train Hard, Fight Easy: Robust Meta Reinforcement Learning

Greedy Poisson Rejection Sampling

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

Time-Independent Information-Theoretic Generalization Bounds for SGLD

Toward Re-Identifying Any Animal

Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies

AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms

Uncertainty-Aware Instance Reweighting for Off-Policy Learning

Adversarially Robust Distributed Count Tracking via Partial Differential Privacy

Online Performative Gradient Descent for Learning Nash Equilibria in Decision-Dependent Games

Functional Renyi Differential Privacy for Generative Modeling

Simple and Asymmetric Graph Contrastive Learning without Augmentations

Efficient Equivariant Transfer Learning from Pretrained Models

Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings

When Does Optimizing a Proper Loss Yield Calibration?

Partial Multi-Label Learning with Probabilistic Graphical Disambiguation

Learning to Group Auxiliary Datasets for Molecule

Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations

On the Relationship Between Relevance and Conflict in Online Social Link Recommendations

QuadAttac$K$: A Quadratic Programming Approach to Learning Ordered Top-$K$ Adversarial Attacks

UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation

Online Nonstochastic Model-Free Reinforcement Learning

Computing Approximate $\ell_p$ Sensitivities

Loss Decoupling for Task-Agnostic Continual Learning

Modeling Dynamics over Meshes with Gauge Equivariant Nonlinear Message Passing

Quantifying the Cost of Learning in Queueing Systems

Self-Supervised Visual Acoustic Matching

DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets

Provably Efficient Algorithm for Nonstationary Low-Rank MDPs

Practical and Asymptotically Exact Conditional Sampling in Diffusion Models

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling

Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation

Behavior Alignment via Reward Function Optimization

Self-Supervised Motion Magnification by Backpropagating Through Optical Flow

Harnessing the power of choices in decision tree learning

Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints

Cross-Episodic Curriculum for Transformer Agents

Hypothesis Selection with Memory Constraints

State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding

Guiding The Last Layer in Federated Learning with Pre-Trained Models

Statistical Knowledge Assessment for Large Language Models

Training neural operators to preserve invariant measures of chaotic attractors

Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models

When is Agnostic Reinforcement Learning Statistically Tractable?

Expressive probabilistic sampling in recurrent neural networks

Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence

Distributionally Robust Skeleton Learning of Discrete Bayesian Networks

Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective

Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests

FLSL: Feature-level Self-supervised Learning

Mechanism Design for Collaborative Normal Mean Estimation

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts

The Grand Illusion: The Myth of Software Portability and Implications for ML Progress.

Kernel Quadrature with Randomly Pivoted Cholesky

Bayesian target optimisation for high-precision holographic optogenetics

Multi-task learning with summary statistics

StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on the Microcontroller

TD Convergence: An Optimization Perspective

Probabilistic Invariant Learning with Randomized Linear Classifiers

Doubly Constrained Fair Clustering

Bayesian Risk-Averse Q-Learning with Streaming Observations

Block-State Transformers

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

Collaboratively Learning Linear Models with Structured Missing Data

Bi-Level Offline Policy Optimization with Limited Exploration

Learning Nonparametric Latent Causal Graphs with Unknown Interventions

QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Uncovering Meanings of Embeddings via Partial Orthogonality

Riemannian Projection-free Online Learning

Online robust non-stationary estimation

Scaling laws for language encoding models in fMRI

LIMA: Less Is More for Alignment

Gradient-Based Feature Learning under Structured Data

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

OKRidge: Scalable Optimal k-Sparse Ridge Regression

Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning

Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks

The s-value: evaluating stability with respect to distributional shifts

Generating Images with Multimodal Language Models

Successor-Predecessor Intrinsic Exploration

Blurred-Dilated Method for Adversarial Attacks

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes

Any-to-Any Generation via Composable Diffusion

OBJECT 3DIT: Language-guided 3D-aware Image Editing

Binarized Neural Machine Translation

A Competitive Algorithm for Agnostic Active Learning

Fine-Tuning Language Models with Just Forward Passes

Robust Concept Erasure via Kernelized Rate-Distortion Maximization

Double Auctions with Two-sided Bandit Feedback

Lower Bounds on Adaptive Sensing for Matrix Recovery

FedNAR: Federated Optimization with Normalized Annealing Regularization

End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics

GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization

Distributed Inference and Fine-tuning of Large Language Models Over The Internet

Mechanic: A Learning Rate Tuner

Going beyond persistent homology using persistent homology

Adaptive Privacy Composition for Accuracy-first Mechanisms

Temporally Disentangled Representation Learning under Unknown Nonstationarity

Evaluating the Moral Beliefs Encoded in LLMs

The Adversarial Consistency of Surrogate Risks for Binary Classification

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning

Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

Context-lumpable stochastic bandits

Embracing the chaos: analysis and diagnosis of numerical instability in variational flows

Diverse Conventions for Human-AI Collaboration

RECKONING: Reasoning through Dynamic Knowledge Encoding

Optimistic Rates for Multi-Task Representation Learning

Neural Priming for Sample-Efficient Adaptation

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

Easy Learning from Label Proportions

Propagating Knowledge Updates to LMs Through Distillation

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

What Planning Problems Can A Relational Neural Network Solve?

Optimal Learners for Realizable Regression: PAC Learning and Online Learning

Fragment-based Pretraining and Finetuning on Molecular Graphs

Non-Stationary Bandits with Auto-Regressive Temporal Dependency

Learning Universal Policies via Text-Guided Video Generation

Resetting the Optimizer in Deep RL: An Empirical Study

When are ensembles really effective?

Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer

Feature Selection in the Contrastive Analysis Setting

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients

On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms

Reliable learning in challenging environments

Learning to Reason and Memorize with Self-Notes

When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels

Intervention Generalization: A View from Factor Graph Models

DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings

Optimal Exploration for Model-Based RL in Nonlinear Systems

Large language models transition from integrating across position-yoked, exponential windows to structure-yoked, power-law windows

Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack

Are Diffusion Models Vision-And-Language Reasoners?

FAMO: Fast Adaptive Multitask Optimization

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous Objects

What Can We Learn from Unlearnable Datasets?

Online Ad Allocation with Predictions

Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback

PAPR: Proximity Attention Point Rendering

On the Sublinear Regret of GP-UCB

On Imitation in Mean-field Games

Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates

Strategic Classification under Unknown Personalized Manipulation

$k$-Means Clustering with Distance-Based Privacy

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics

SE(3) Equivariant Augmented Coupling Flows

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales

Bridging RL Theory and Practice with the Effective Horizon

Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks

Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise

Meek Separators and Their Applications in Targeted Causal Discovery

Students Parrot Their Teachers: Membership Inference on Model Distillation

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness

Exact recovery and Bregman hard clustering of node-attributed Stochastic Block Model

Evaluating Neuron Interpretation Methods of NLP Models

Composing Parameter-Efficient Modules with Arithmetic Operation

Conformal Prediction for Time Series with Modern Hopfield Networks

Generalized equivalences between subsampling and ridge regularization

Convolutional Neural Operators for robust and accurate learning of PDEs

LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas

Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism

Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric

Triple Eagle: Simple, Fast and Practical Budget-Feasible Mechanisms

Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization

FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space

A Bounded Ability Estimation for Computerized Adaptive Testing

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective

Task-aware world model learning with meta weighting via bi-level optimization

A Scalable Neural Network for DSIC Affine Maximizer Auction Design

SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

Dynamic Personalized Federated Learning with Adaptive Differential Privacy

A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability

Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification

Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning

Self-supervised Graph Neural Networks via Low-Rank Decomposition

UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

GALOPA: Graph Transport Learning with Optimal Plan Alignment

Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings

ResMem: Learn what you can and memorize the rest

PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation

A Batch-to-Online Transformation under Random-Order Model

A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation

Aligning Synthetic Medical Images with Clinical Knowledge using Human Feedback

Thrust: Adaptively Propels Large Language Models with External Knowledge

CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection

RRHF: Rank Responses to Align Language Models with Human Feedback

Learning Modulated Transformation in GANs

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

Lightweight Vision Transformer with Bidirectional Interaction

Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms

Language Models can Solve Computer Tasks

Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games

Single-Stage Visual Query Localization in Egocentric Videos

Meta-Adapter: An Online Few-shot Learner for Vision-Language Model

Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective

Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks

Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space

A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm

Balanced Training for Sparse GANs

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction

Towards Efficient Pre-Trained Language Model via Feature Correlation Distillation

Fast Partitioned Learned Bloom Filter

Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network

Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks

Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval

On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds

H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training

Test-Time Distribution Normalization for Contrastively Learned Visual-language Models

RanPAC: Random Projections and Pre-trained Models for Continual Learning

Learning non-Markovian Decision-Making from State-only Sequences

Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs

Training Private Models That Know What They Don’t Know

Improving Diffusion-Based Image Synthesis with Context Prediction

HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork

Deep Momentum Multi-Marginal Schrödinger Bridge

An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations

False Discovery Proportion control for aggregated Knockoffs

Max-Margin Token Selection in Attention Mechanism

Block-Coordinate Methods and Restarting for Solving Extensive-Form Games

Video Prediction Models as Rewards for Reinforcement Learning

A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs

Core-sets for Fair and Diverse Data Summarization

Spectral Evolution and Invariance in Linear-width Neural Networks

Agnostic Multi-Group Active Learning

DropCompute: simple and more robust distributed synchronous training via compute variance reduction

Dynamic Pricing and Learning with Bayesian Persuasion

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions

A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning

Learning Unseen Modality Interaction

A One-Size-Fits-All Approach to Improving Randomness in Paper Assignment

Synthetic Experience Replay

Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data

Symbolic Discovery of Optimization Algorithms

Predict-then-Calibrate: A New Perspective of Robust Contextual LP

Face Reconstruction from Facial Templates by Learning Latent Space of a Generator Network

Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis

ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking

Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning

Tight Bounds for Volumetric Spanners and Applications

Online Convex Optimization with Unbounded Memory

Tanimoto Random Features for Scalable Molecular Machine Learning

Learning World Models with Identifiable Factorization

SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data

Structured Federated Learning through Clustered Additive Modeling

Learning and Collusion in Multi-unit Auctions

IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

Beyond probability partitions: Calibrating neural networks with semantic aware grouping

MixFormerV2: Efficient Fully Transformer Tracking

Tight Risk Bounds for Gradient Descent on Separable Data

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent

Model Spider: Learning to Rank Pre-Trained Models Efficiently

HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds

Federated Learning with Manifold Regularization and Normalized Update Reaggregation

Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction

Eliminating Domain Bias for Federated Learning in Representation Space

Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses

Slot-guided Volumetric Object Radiance Fields

(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy

Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Trans-Dimensional Generative Modeling via Jump Diffusion Models

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective

ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning

Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics

Crystal Structure Prediction by Joint Equivariant Diffusion

ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction

Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals

Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials

From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation

Contrastive Sampling Chains in Diffusion Models

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

Towards Distribution-Agnostic Generalized Category Discovery

Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training

Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction

Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions

Spectral Co-Distillation for Personalized Federated Learning

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects

PTQD: Accurate Post-Training Quantization for Diffusion Models

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Optimal Treatment Regimes for Proximal Causal Learning

Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Large Language Models can Implement Policy Iteration

iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models

Global Optimality in Bivariate Gradient-based DAG Learning

A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains

Truly Scale-Equivariant Deep Nets with Fourier Layers

Inverse Preference Learning: Preference-based RL without a Reward Function

Neural Functional Transformers

Permutation Equivariant Neural Functionals

Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation

Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head

Online Constrained Meta-Learning: Provable Guarantees for Generalization

Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars

Adaptive Selective Sampling for Online Prediction with Experts

Coneheads: Hierarchy Aware Attention

A Measure-Theoretic Axiomatisation of Causality

Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback

Text-to-Image Diffusion Models are Zero Shot Classifiers

REx: Data-Free Residual Quantization Error Expansion

PointGPT: Auto-regressively Generative Pre-training from Point Clouds

Robust Model Reasoning and Fitting via Dual Sparsity Pursuit

Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games

FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow

GlyphControl: Glyph Conditional Control for Visual Text Generation

Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations

Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL

LLM-Pruner: On the Structural Pruning of Large Language Models

Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function

LuminAIRe: Illumination-Aware Conditional Image Repainting for Lighting-Realistic Generation

Latent exploration for Reinforcement Learning

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning

Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation

Generative Category-level Object Pose Estimation via Diffusion Models

Generalized Weighted Path Consistency for Mastering Atari Games

Towards Better Dynamic Graph Learning: New Architecture and Unified Library

Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation

Masked Image Residual Learning for Scaling Deeper Vision Transformers

No-Regret Learning in Dynamic Competition with Reference Effects Under Logit Demand

Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features

HubRouter: Learning Global Routing via Hub Generation and Pin-hub Connection

Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities

Demystifying Softmax Gating Function in Gaussian Mixture of Experts

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions

Knowledge Distillation for High Dimensional Search Index

Accelerating Value Iteration with Anchoring

One Fits All: Power General Time Series Analysis by Pretrained LM

Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration

One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning

Diffusion Probabilistic Models for Structured Node Classification

Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation

Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Robust Lipschitz Bandits to Adversarial Corruptions

Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems

Energy-Based Sliced Wasserstein Distance

Riemannian Residual Neural Networks

Estimating Riemannian Metric with Noise-Contaminated Intrinsic Distance

One-Step Diffusion Distillation via Deep Equilibrium Models

Multi-Player Zero-Sum Markov Games with Networked Separable Interactions

Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective

Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value

Certifiably Robust Graph Contrastive Learning

Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards

Latent Graph Inference with Limited Supervision

Latent Field Discovery in Interacting Dynamical Systems with Neural Fields

Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision

Strategic Data Sharing between Competitors

Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy Continuation

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

Unifying GANs and Score-Based Diffusion as Generative Particle Models

Rank-DETR for High Quality Object Detection

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks

Regularization properties of adversarially-trained linear regression

On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data

Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion

Greatness in Simplicity: Unified Self-Cycle Consistency for Parser-Free Virtual Try-On

Exploring Question Decomposition for Zero-Shot VQA

PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

SEGA: Instructing Text-to-Image Models using Semantic Guidance

High-dimensional Contextual Bandit Problem without Sparsity

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

Bayesian Learning via Q-Exponential Process

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks

Learning Energy-based Model via Dual-MCMC Teaching

Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting

Uncertainty Quantification via Neural Posterior Principal Components

FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks

Contextual Stochastic Bilevel Optimization

Multi-Head Adapter Routing for Cross-Task Generalization

Cal-DETR: Calibrated Detection Transformer

Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods

Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models

PHOTOSWAP: Personalized Subject Swapping in Images

Unpaired Multi-Domain Causal Representation Learning

Characterization and Learning of Causal Graphs with Small Conditioning Sets

Active Learning for Semantic Segmentation with Multi-class Label Query

Thinker: Learning to Plan and Act

Horospherical Decision Boundaries for Large Margin Classification in Hyperbolic Space

Coordinating Distributed Example Orders for Provably Accelerated Training

FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout

Explainable Brain Age Prediction using coVariance Neural Networks

Learning with Explanation Constraints

Locality-Aware Generalizable Implicit Neural Representation

Language Semantic Graph Guided Data-Efficient Learning

Compression with Bayesian Implicit Neural Representations

ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion

Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes

Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs

Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy

Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback

Transfer learning for atomistic simulations using GNNs and kernel mean embeddings

Adaptive Principal Component Regression with Applications to Panel Data

DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models

AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis

A Metadata-Driven Approach to Understand Graph Neural Networks

Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning

Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization

Regret Matching+: (In)Stability and Fast Convergence in Games

SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits

VRA: Variational Rectified Activation for Out-of-distribution Detection

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning

Flow: Per-instance Personalized Federated Learning

CP-SLAM: Collaborative Neural Point-based SLAM System

Trading-off price for data quality to achieve fair online allocation

Optimizing over trained GNNs via symmetry breaking

Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery

Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment

Normalization-Equivariant Neural Networks with Application to Image Denoising

Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem

Post-processing Private Synthetic Data for Improving Utility on Selected Measures

GEX: A flexible method for approximating influence via Geometric Ensemble

Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis

Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach

Composable Coresets for Determinant Maximization: Greedy is Almost Optimal

Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models

Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy

Fast Optimal Transport through Sliced Generalized Wasserstein Geodesics

GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning

HyTrel: Hypergraph-enhanced Tabular Data Representation Learning

Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences

Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration

Evaluating Cognitive Maps and Planning in Large Language Models with CogEval

Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing

Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices

Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

Unsupervised Anomaly Detection with Rejection

Anchor Data Augmentation

Meta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning

PreDiff: Precipitation Nowcasting with Latent Diffusion Models

A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction

Global Structure-Aware Diffusion Process for Low-light Image Enhancement

How a Student becomes a Teacher: learning and forgetting through Spectral methods

Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent

Learning Rate Free Sampling in Constrained Domains

Safety Verification of Decision-Tree Policies in Continuous Time

Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation

Binary Classification with Confidence Difference

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

Efficient Model-Free Exploration in Low-Rank MDPs

GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies

When Does Confidence-Based Cascade Deferral Suffice?

Dynamically Masked Discriminator for GANs

A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression

Combating Bilateral Edge Noise for Robust Link Prediction

SLIBO-Net: Floorplan Reconstruction via Slicing Box Representation with Local Geometry Regularization

Globally injective and bijective neural operators

Mutual-Information Regularized Multi-Agent Policy Iteration

Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation

Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning

Understanding Contrastive Learning via Distributionally Robust Optimization

MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection

Learning Large-Scale MTP$_2$ Gaussian Graphical Models via Bridge-Block Decomposition

Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems

Black-Box Differential Privacy for Interactive ML

Connecting Multi-modal Contrastive Representations

Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification

A Theory of Unsupervised Translation Motivated by Understanding Animal Communication

Bias in Evaluation Processes: An Optimization-Based Model

SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Discrete-Smoothness in Online Algorithms with Predictions

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability

A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing

Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications

Relative Entropic Optimal Transport: a (Prior-aware) Matching Perspective to (Unbalanced) Classification

Revisiting Adversarial Robustness Distillation from the Perspective of Robust Fairness

Generalised f-Mean Aggregation for Graph Neural Networks

Self-Adaptive Motion Tracking against On-body Displacement of Flexible Sensors

DELTA: Diverse Client Sampling for Fasting Federated Learning

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion

Multi-Step Generalized Policy Improvement by Leveraging Approximate Models

Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph

SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning

Towards Consistent Video Editing with Text-to-Image Diffusion Models

Opening the Vocabulary of Egocentric Actions

Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models

Finite-Time Analysis of Single-Timescale Actor-Critic

A fast heuristic to optimize time-space tradeoff for large models

Geometric Algebra Transformer

STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning

From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

Penalising the biases in norm regularisation enforces sparsity

Conservative Offline Policy Adaptation in Multi-Agent Games

On Certified Generalization in Structured Prediction

Is Distance Matrix Enough for Geometric Deep Learning?

What You See is What You Read? Improving Text-Image Alignment Evaluation

Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser

Point Cloud Completion with Pretrained Text-to-Image Diffusion Models

CQM: Curriculum Reinforcement Learning with a Quantized World Model

Chatting Makes Perfect: Chat-based Image Retrieval

Idempotent Learned Image Compression with Right-Inverse

Neural Fields with Hard Constraints of Arbitrary Differential Order

Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

Language-driven Scene Synthesis using Multi-conditional Diffusion Model

PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising

Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

Score-based Data Assimilation

SODA: Robust Training of Test-Time Data Adaptors

RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing

Macro Placement by Wire-Mask-Guided Black-Box Optimization

Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration

Learning Energy-Based Prior Model with Diffusion-Amortized MCMC

Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction

Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization

DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

Reward Imputation with Sketching for Contextual Batched Bandits

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules

Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval

PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference

Topological RANSAC for instance verification and retrieval without fine-tuning

Non-Asymptotic Analysis of a UCB-based Top Two Algorithm

Lovász Principle for Unsupervised Graph Representation Learning

MathNAS: If Blocks Have a Role in Mathematical Architecture Design

Orthogonal Non-negative Tensor Factorization based Multi-view Clustering

Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions

Optimized Covariance Design for AB Test on Social Network under Interference

Off-Policy Evaluation for Human Feedback

Non-adversarial training of Neural SDEs with signature kernel scores

Separable Physics-Informed Neural Networks

Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck

Exposing Attention Glitches with Flip-Flop Language Modeling

Goal-conditioned Offline Planning from Curious Exploration

Offline Reinforcement Learning with Differential Privacy

FaceComposer: A Unified Model for Versatile Facial Content Creation

Neural (Tangent Kernel) Collapse

Harnessing Hard Mixed Samples with Decoupled Regularizer

Collaborative Alignment of NLP Models

IEBins: Iterative Elastic Bins for Monocular Depth Estimation

VanillaNet: the Power of Minimalism in Deep Learning

AbDiffuser: full-atom generation of in-vitro functioning antibodies

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models

FedFed: Feature Distillation against Data Heterogeneity in Federated Learning

Gradient-Free Kernel Stein Discrepancy

Fairness-guided Few-shot Prompting for Large Language Models

Scattering Vision Transformer: Spectral Mixing Matters

Encoding Human Behavior in Information Design through Deep Learning

Recovering Unbalanced Communities in the Stochastic Block Model with Application to Clustering with a Faulty Oracle

Attentive Transfer Entropy to Exploit Transient Emergence of Coupling Effect

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Sequential Subset Matching for Dataset Distillation

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources

FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

Distributionally Robust Bayesian Optimization with $\varphi$-divergences

Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense

Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL

Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks

FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Solving Inverse Physics Problems with Score Matching

DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models

Diffusion-Based Probabilistic Uncertainty Estimation for Active Domain Adaptation

VideoComposer: Compositional Video Synthesis with Motion Controllability

Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval

K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing

Collaborative Learning via Prediction Consensus

Principled Weight Initialisation for Input-Convex Neural Networks

What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement.

Spontaneous symmetry breaking in generative diffusion models

GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction

Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts

One-step differentiation of iterative algorithms

DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth Adaptation

Learning Generalizable Agents via Saliency-guided Features Decorrelation

R-divergence for Estimating Model-oriented Distribution Discrepancy

Kernelized Reinforcement Learning with Order Optimal Regret Bounds

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

AIMS: All-Inclusive Multi-Level Segmentation for Anything

Segment Anything in 3D with NeRFs

Optimization or Architecture: How to Hack Kalman Filtering

ASPEN: Breaking Operator Barriers for Efficient Parallelization of Deep Neural Networks

MultiMoDN—Multimodal, Multi-Task, Interpretable Modular Networks

Improving Adversarial Robustness via Information Bottleneck Distillation

Imbalanced Mixed Linear Regression

L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors

BIOT: Biosignal Transformer for Cross-data Learning in the Wild

Formulating Discrete Probability Flow Through Optimal Transport

Universal Prompt Tuning for Graph Neural Networks

Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger

On Sparse Modern Hopfield Model

Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions

Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction

Cause-Effect Inference in Location-Scale Noise Models: Maximum Likelihood vs. Independence Testing

SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models

Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers

Closing the gap between the upper bound and lower bound of Adam's iteration complexity

Training Your Image Restoration Network Better with Random Weight Network as Optimization Function

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Conformalized matrix completion

A Heavy-Tailed Algebra for Probabilistic Programming

What Knowledge Gets Distilled in Knowledge Distillation?

Large-Scale Distributed Learning via Private On-Device LSH

Abide by the law and follow the flow: conservation laws for gradient flows

Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images

The Target-Charging Technique for Privacy Analysis across Interactive Computations

SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting

Efficient Online Clustering with Moving Costs

On the Implicit Bias of Linear Equivariant Steerable Networks

A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process

Improving Robustness with Adaptive Weight Decay

Calibrating “Cheap Signals” in Peer Review without a Prior

Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces

Towards Label-free Scene Understanding by Vision Foundation Models

ESSEN: Improving Evolution State Estimation for Temporal Networks using Von Neumann Entropy

Learning Robust Statistics for Simulation-based Inference under Model Misspecification

Momentum Provably Improves Error Feedback!

Strategic Apple Tasting

Sharp Bounds for Generalized Causal Sensitivity Analysis

Better Private Linear Regression Through Better Private Feature Selection

Multiplication-Free Transformer Training via Piecewise Affine Operations

Random-Access Infinite Context Length for Transformers

Aligning Gradient and Hessian for Neural Signed Distance Function

Strategyproof Voting under Correlated Beliefs

A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)

Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

Evaluating and Inducing Personality in Pre-trained Language Models

Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence

Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness

Provable Guarantees for Neural Networks via Gradient Feature Learning

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds

Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models

Q-DM: An Efficient Low-bit Quantized Diffusion Model

Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes

Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition

Type-to-Track: Retrieve Any Object via Prompt-based Tracking

Jailbroken: How Does LLM Safety Training Fail?

On the Adversarial Robustness of Out-of-distribution Generalization Models

Deductive Verification of Chain-of-Thought Reasoning

A normative theory of social conflict

Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning

DISCOVER: Making Vision Networks Interpretable via Competition and Dissection

Efficient Activation Function Optimization through Surrogate Modeling

Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory

Replicable Clustering

Scale-Space Hypernetworks for Efficient Biomedical Image Analysis

EDGI: Equivariant Diffusion for Planning with Embodied Agents

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization

OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding

Smoothed Online Learning for Prediction in Piecewise Affine Systems

Optimization of Inter-group criteria for clustering with minimum size constraints

Kiki or Bouba? Sound Symbolism in Vision-and-Language Models

On the Constrained Time-Series Generation Problem

SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians

TransHP: Image Classification with Hierarchical Prompting

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Pointwise uncertainty quantification for sparse variational Gaussian process regression with a Brownian motion prior

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation

What Truly Matters in Trajectory Prediction for Autonomous Driving?

InsActor: Instruction-driven Physics-based Characters

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives

Semi-Supervised Contrastive Learning for Deep Regression with Ordinal Rankings from Spectral Seriation

Adaptive Uncertainty Estimation via High-Dimensional Testing on Latent Representations

Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation

Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model

2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression

On student-teacher deviations in distillation: does it pay to disobey?

SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model

Inferring Hybrid Neural Fluid Fields from Videos

On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training

Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data

Autodecoding Latent 3D Diffusion Models

Emergent Correspondence from Image Diffusion

Convolutional Visual Prompt for Robust Visual Perception

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection

Transformers over Directed Acyclic Graphs

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

Does Graph Distillation See Like Vision Dataset Counterpart?

Modeling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network

MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data

Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings

Diversifying Spatial-Temporal Perception for Video Domain Generalization

VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens

How many samples are needed to leverage smoothness?

OpenMask3D: Open-Vocabulary 3D Instance Segmentation

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

Reading Relevant Feature from Global Representation Memory for Visual Object Tracking

GMSF: Global Matching Scene Flow

Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data

Causal Discovery from Subsampled Time Series with Proxy Variables

A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories

Demographic Parity Constrained Minimax Optimal Regression under Linear Model

Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors

ClusterFomer: Clustering As A Universal Visual Learner

Data-Centric Learning from Unlabeled Graphs with Diffusion Model

Streaming Factor Trajectory Learning for Temporal Tensor Decomposition

Offline Imitation Learning with Variational Counterfactual Reasoning

BERT Lost Patience Won't Be Robust to Adversarial Slowdown

Label-efficient Segmentation via Affinity Propagation

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

No-regret Algorithms for Fair Resource Allocation

DiffUTE: Universal Text Editing Diffusion Model

Stable Diffusion is Unstable

Unified 3D Segmenter As Prototypical Classifiers

Learning Motion Refinement for Unsupervised Face Animation

Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes

Learning Large Graph Property Prediction via Graph Segment Training

Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera

Variational Inference with Gaussian Score Matching

Block Broyden's Methods for Solving Nonlinear Equations

Real-World Image Variation by Aligning Diffusion Inversion Chain

Full-Atom Protein Pocket Design via Iterative Refinement

Adversarial Training from Mean Field Perspective

Deep Patch Visual Odometry

You Only Condense Once: Two Rules for Pruning Condensed Datasets

Online Map Vectorization for Autonomous Driving: A Rasterization Perspective

GPEX, A Framework For Interpreting Artificial Neural Networks

Efficient Symbolic Policy Learning with Differentiable Symbolic Expression

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models

Epistemic Neural Networks

Self-supervised Object-Centric Learning for Videos

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Online Learning under Adversarial Nonlinear Constraints

A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm

SoundCam: A Dataset for Finding Humans Using Room Acoustics

Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning

SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting

The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications

Practical Equivariances via Relational Conditional Neural Processes

Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark

BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data

On the Convergence of Encoder-only Shallow Transformers

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models

BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting

Objaverse-XL: A Universe of 10M+ 3D Objects

AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution

Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

FIND: A Function Description Benchmark for Evaluating Interpretability Methods

Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning

DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology

Semi-Implicit Denoising Diffusion Models (SIDDMs)

Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data

WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design

Aligning Language Models with Human Preferences via a Bayesian Approach

SARAMIS: Simulation Assets for Robotic Assisted and Minimally Invasive Surgery

FLAIR : a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery

Enhancing Sharpness-Aware Optimization Through Variance Suppression

CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography

FELM: Benchmarking Factuality Evaluation of Large Language Models

TWIGMA: A dataset of AI-Generated Images with Metadata From Twitter

ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition

GenS: Generalizable Neural Surface Reconstruction from Multi-View Images

Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking

Data Pruning via Moving-one-Sample-out

Rehearsal Learning for Avoiding Undesired Future

CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews

Characteristic Circuits

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

AiluRus: A Scalable ViT Framework for Dense Prediction

Generator Born from Classifier

BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks

Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses

$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties

Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery

RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection

Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance

DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models

GenEval: An object-focused framework for evaluating text-to-image alignment

CHAMMI: A benchmark for channel-adaptive models in microscopy imaging

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation

Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching

SEENN: Towards Temporal Spiking Early Exit Neural Networks

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

Consensus and Subjectivity of Skin Tone Annotation for ML Fairness

HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models

NAP: Neural 3D Articulated Object Prior

Segment Everything Everywhere All at Once

Module-wise Training of Neural Networks via the Minimizing Movement Scheme

ProteinInvBench: Benchmarking Protein Inverse Folding on Diverse Tasks, Models, and Metrics

MLFMF: Data Sets for Machine Learning for Mathematical Formalization

Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection

Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation

PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning

AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems

ProteinShake: Building datasets and benchmarks for deep learning on protein structures

Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning

The expressive power of pooling in Graph Neural Networks

QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Your Data

Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization

UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction

SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics

Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends

Networks are Slacking Off: Understanding Generalization Problem in Image Deraining

Semantic Image Synthesis with Unconditional Generator

WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction

Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark

When Visual Prompt Tuning Meets Source-Free Domain Adaptive Semantic Segmentation

HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count

Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine

Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation

Non-Rigid Shape Registration via Deep Functional Maps Prior

Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration

Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms

STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events

Mitigating Source Bias for Fairer Weak Supervision

$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models

Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning

Data-Driven Network Neuroscience: On Data Collection and Benchmark

HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding

On the Convergence of Black-Box Variational Inference

Generating QM1B with PySCF$_{\text{IPU}}$

Learning to Taste: A Multimodal Wine Dataset

On Private and Robust Bandits

VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception

WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts

Learning to Augment Distributions for Out-of-distribution Detection

Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties

StressID: a Multimodal Dataset for Stress Identification

Quilt-1M: One Million Image-Text Pairs for Histopathology

Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping

EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis

CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection

The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes

DynPoint: Dynamic Neural Point For View Synthesis

Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts

PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change

MVDoppler: Unleashing the Power of Multi-View Doppler for MicroMotion-based Gait Classification

SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis

Enhancing Motion Deblurring in High-Speed Scenes with Spike Streams

M$^{2}$SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors

On the Ability of Graph Neural Networks to Model Interactions Between Vertices

CODA: Generalizing to Open and Unseen Domains with Compaction and Disambiguation

InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion

Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning

ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents

Scaling Laws for Hyperparameter Optimization

A Smooth Binary Mechanism for Efficient Private Continual Observation

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

DISCS: A Benchmark for Discrete Sampling

MotionGPT: Human Motion as a Foreign Language

SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality

A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning

OpenProteinSet: Training data for structural biology at scale

Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile

DataComp: In search of the next generation of multimodal datasets

How hard are computer vision datasets? Calibrating dataset difficulty to viewing time

M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

RaLEs: a Benchmark for Radiology Language Evaluations

Unsupervised Graph Neural Architecture Search with Disentangled Self-Supervision

M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark

A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning

LOVM: Language-Only Vision Model Selection

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs

Holistic Evaluation of Text-to-Image Models

ToolQA: A Dataset for LLM Question Answering with External Tools

ChessGPT: Bridging Policy Learning and Language Modeling

Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT

FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation

Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

Generalizing Nonlinear ICA Beyond Structural Sparsity

Lexinvariant Language Models

INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms

On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets

AVIDa-hIL6: A Large-Scale VHH Dataset Produced from an Immunized Alpaca for Predicting Antigen-Antibody Interactions

Improving multimodal datasets with image captioning

GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition

PyNeRF: Pyramidal Neural Radiance Fields

What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation

SPRING: Studying Papers and Reasoning to play Games

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

Boundary Guided Learning-Free Semantic Control with Diffusion Models

The ToMCAT Dataset

Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions

SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models

StyleGAN knows Normal, Depth, Albedo, and More

Exploring Why Object Recognition Performance Degrades Across Income Levels and Geographies with Factor Annotations

Variational Gaussian Processes with Decoupled Conditionals

A Massive Scale Semantic Similarity Dataset of Historical English

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities

Are These the Same Apple? Comparing Images Based on Object Intrinsics

Generalizable One-shot 3D Neural Head Avatar

American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers

SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

Information Design in Multi-Agent Reinforcement Learning

D4: Improving LLM Pretraining via Document De-Duplication and Diversification

A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset

RoboHive: A Unified Framework for Robot Learning

Mind2Web: Towards a Generalist Agent for the Web

How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

GEO-Bench: Toward Foundation Models for Earth Monitoring

COOM: A Game Benchmark for Continual Reinforcement Learning

HeadSculpt: Crafting 3D Head Avatars with Text

trajdata: A Unified Interface to Multiple Human Trajectory Datasets

DynaDojo: An Extensible Platform for Benchmarking Scaling in Dynamical System Identification

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset

AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling

LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day

Benchmarking Robustness to Adversarial Image Obfuscations

DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection

Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources

Realistic Synthetic Financial Transactions for Anti-Money Laundering Models

Object Reprojection Error (ORE): Camera pose benchmarks from lightweight tracking annotations

Learning Domain-Aware Detection Head with Prompt Tuning

CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care

Multi-modal Queried Object Detection in the Wild

OceanBench: The Sea Surface Height Edition

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection

Social Motion Prediction with Cognitive Hierarchies

A Dataset for Analyzing Streaming Media Performance over HTTP/3 Browsers

Data Portraits: Recording Foundation Model Training Data

HT-Step: Aligning Instructional Articles with How-To Videos

Renku: a platform for sustainable data science

Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias

Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method

Pairwise GUI Dataset Construction Between Android Phones and Tablets

Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark

A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models

SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning

GSLB: The Graph Structure Learning Benchmark

RD-Suite: A Benchmark for Ranking Distillation

NetHack is Hard to Hack

DISCO-10M: A Large-Scale Music Dataset

The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification

Evaluating Open-QA Evaluation

Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials

Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

RADAR: Robust AI-Text Detection via Adversarial Learning

Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure

Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation

Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor

Training Neural Networks is NP-Hard in Fixed Dimension

Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition

PCF-GAN: generating sequential data via the characteristic function of measures on the path space

D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts

Prefix-Tree Decoding for Predicting Mass Spectra from Molecules

Finding Safe Zones of Markov Decision Processes Policies

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities

Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization

VPGTrans: Transfer Visual Prompt Generator across LLMs

Sharp Calibrated Gaussian Processes

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking

Unlocking Deterministic Robustness Certification on ImageNet

Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation

4D Panoptic Scene Graph Generation

Katakomba: Tools and Benchmarks for Data-Driven NetHack

Gigastep - One Billion Steps per Second Multi-agent Reinforcement Learning

No Representation Rules Them All in Category Discovery

PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection

Best Arm Identification with Fixed Budget: A Large Deviation Perspective

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

VoxDet: Voxel Learning for Novel Instance Detection

L2T-DLN: Learning to Teach with Dynamic Loss Network

A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship

NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks

MultiVENT: Multilingual Videos of Events and Aligned Natural Text

STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection

A Dataset of Relighted 3D Interacting Hands

IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL

Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Language-based Action Concept Spaces Improve Video Self-Supervised Learning

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

Revisiting the Evaluation of Image Synthesis with GANs

Tanh Works Better with Asymmetry

Active Reasoning in an Open-World Environment

NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications

EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images

UDC-SIT: A Real-World Dataset for Under-Display Cameras

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

OV-PARTS: Towards Open-Vocabulary Part Segmentation

Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis

Mr. HiSum: A Large-scale Dataset for Video Highlight Detection and Summarization

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths

Learning Human Action Recognition Representations Without Real Humans

Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry

C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

Cola: A Benchmark for Compositional Text-to-image Retrieval

Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback

AQuA: A Benchmarking Tool for Label Quality Assessment

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias

M$^2$Hub: Unlocking the Potential of Machine Learning for Materials Discovery

DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation

A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence

Improving CLIP Training with Language Rewrites

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

OpenDataVal: a Unified Benchmark for Data Valuation

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

Uncovering Neural Scaling Laws in Molecular Representation Learning

Learning Curves for Deep Structured Gaussian Feature Models

Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

The Cambridge Law Corpus: A Corpus for Legal AI Research

Beyond Confidence: Reliable Models Should Also Consider Atypicality

OFCOURSE: A Multi-Agent Reinforcement Learning Environment for Order Fulfillment

Does progress on ImageNet transfer to real-world datasets?

Ethical Considerations for Responsible Data Curation

Active Vision Reinforcement Learning under Limited Visual Observability

PTADisc: A Cross-Course Dataset Supporting Personalized Learning in Cold-Start Scenarios

Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection

Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation

Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

EPIC Fields: Marrying 3D Geometry and Video Understanding

FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding

Compact Neural Volumetric Video Representations with Dynamic Codebooks

Training Energy-Based Normalizing Flow with Score-Matching Objectives

Metropolis Sampling for Constrained Diffusion Models

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

OpenAssistant Conversations - Democratizing Large Language Model Alignment

Learning To Dive In Branch And Bound

RealTime QA: What's the Answer Right Now?

Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping

Building Socio-culturally Inclusive Stereotype Resources with Community Engagement

Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

Mathematical Capabilities of ChatGPT

DeWave: Discrete Encoding of EEG Waves for EEG to Text Translation

How to Data in Datathons

EV-Eye: Rethinking High-frequency Eye Tracking through the Lenses of Event Cameras

Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity

Alexa Arena: A User-Centric Interactive Platform for Embodied AI

SG×P : A Sorghum Genotype × Phenotype Prediction Dataset and Benchmark

The Waymo Open Sim Agents Challenge

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

Towards Higher Ranks via Adversarial Weight Pruning

A High-Resolution Dataset for Instance Detection with Multi-View Object Capture

Optimal Transport-Guided Conditional Score-Based Diffusion Model

Towards a Comprehensive Benchmark for High-Level Synthesis Targeted to FPGAs

Natural Language Instruction-following with Task-related Language Development and Translation

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement

DAC-DETR: Divide the Attention Layers and Conquer

PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance

rPPG-Toolbox: Deep Remote PPG Toolbox

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation

Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory

DVSOD: RGB-D Video Salient Object Detection

Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation

BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing

Interactive Visual Reasoning under Uncertainty

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

Elastic Decision Transformer

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase

Temporal Robustness against Data poisoning

Focus Your Attention when Few-Shot Classification

Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns

Real3D-AD: A Dataset of Point Cloud Anomaly Detection

Puzzlefusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving

Temporal Graph Benchmark for Machine Learning on Temporal Graphs

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

Learning Time-Invariant Representations for Individual Neurons from Population Dynamics

RGMIL: Guide Your Multiple-Instance Learning Model with Regressor

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

A Comprehensive Benchmark for Neural Human Radiance Fields

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

Should We Learn Most Likely Functions or Parameters?

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

Protein Design with Guided Discrete Diffusion

OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects

EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary Information

MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning

AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation

Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition

Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models

ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification

Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context

Low-shot Object Learning with Mutual Exclusivity Bias

ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning

How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception

Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

Parallel-mentoring for Offline Model-based Optimization

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

Predicting a Protein's Stability under a Million Mutations

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors

Faster Differentially Private Convex Optimization via Second-Order Methods

Counting Distinct Elements Under Person-Level Differential Privacy

Privacy Auditing with One (1) Training Run

LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case

JourneyDB: A Benchmark for Generative Image Understanding

Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples

Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text

VidChapters-7M: Video Chapters at Scale

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations

WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes

TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph

Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner

Degraded Polygons Raise Fundamental Questions of Neural Network Perception

Benchmarking Large Language Models on CMExam - A comprehensive Chinese Medical Exam Dataset

Benchmarking Foundation Models with Language-Model-as-an-Examiner

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution

Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis

BiMatting: Efficient Video Matting via Binarization

Segment Anything in High Quality

CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data

Benchmarking Encoder-Decoder Architectures for Biplanar X-ray to 3D Bone Shape Reconstruction

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learning

Validated Image Caption Rating Dataset

Video Timeline Modeling For News Story Understanding

Learning Trajectories are Generalization Indicators

Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion

3D-Aware Visual Question Answering about Parts, Poses and Occlusions

Reinforcement Learning with Fast and Forgetful Memory

Benchmarking Distribution Shift in Tabular Data with TableShift

Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

Hierarchical Open-vocabulary Universal Image Segmentation

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs

When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment

DAW: Exploring the Better Weighting Function for Semi-supervised Semantic Segmentation

LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering

ADGym: Design Choices for Deep Anomaly Detection

Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones

LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios

The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only

Binarized Spectral Compressive Imaging

AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web

SiT Dataset: Socially Interactive Pedestrian Trajectory Dataset for Social Navigation Robots

LithoBench: Benchmarking AI Computational Lithography for Semiconductor Manufacturing

Lo-Hi: Practical ML Drug Discovery Benchmark

Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation

Sharpness-Aware Minimization Leads to Low-Rank Features

Evaluating Self-Supervised Learning for Molecular Graph Embeddings

CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes

Revealing the unseen: Benchmarking video action recognition under occlusion

CMMA: Benchmarking Multi-Affection Detection in Chinese Multi-Modal Conversations

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

Understanding Social Reasoning in Language Models with Language Models

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design

Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework

Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers

Contrastive Training of Complex-Valued Autoencoders for Object Discovery

Towards Stable Backdoor Purification through Feature Shift Tuning

Deep Contract Design via Discontinuous Networks

Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

On the Generalization Properties of Diffusion Models

Collaborative Score Distillation for Consistent Visual Editing

Multi-scale Diffusion Denoised Smoothing

Improving Language Plasticity via Pretraining with Active Forgetting

Alternation makes the adversary weaker in two-player games

Graph Contrastive Learning with Stable and Scalable Spectral Encoding

Textually Pretrained Speech Language Models

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections

Effective Bayesian Heteroscedastic Regression with Deep Neural Networks

Continuous-Time Functional Diffusion Processes

One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models

Learning Adaptive Tensorial Density Fields for Clean Cryo-ET Reconstruction

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization

On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection

Disentangling Cognitive Diagnosis with Limited Exercise Labels

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

(Amplified) Banded Matrix Factorization: A unified approach to private training

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy

Adversarial Robustness through Random Weight Sampling

Language Models Meet World Models: Embodied Experiences Enhance Language Models

Model-enhanced Vector Index

Beyond Normal: On the Evaluation of Mutual Information Estimators

ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns

Representational Strengths and Limitations of Transformers

Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms

Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares

A Spectral Theory of Neural Prediction and Alignment

Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective

A Cross-Moment Approach for Causal Effect Estimation

Learning the Efficient Frontier

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information

Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills

3D Indoor Instance Segmentation in an Open-World

DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

Generalization bounds for neural ordinary differential equations and deep residual networks

Spike-driven Transformer

Learning threshold neurons via edge of stability

Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration

NeRF-IBVS: Visual Servo Based on NeRF for Visual Localization and Navigation

Image Captioners Are Scalable Vision Learners Too

Boosting Adversarial Transferability by Achieving Flat Local Maxima

To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis

Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs

LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective

Dynamic Sparsity Is Channel-Level Sparsity Learner

Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

Don’t just prune by magnitude! Your mask topology is a secret weapon

Transfer Learning with Affine Model Transformation

Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

Spiking PointNet: Spiking Neural Networks for Point Clouds

Episodic Multi-Task Learning with Heterogeneous Neural Processes

PaintSeg: Painting Pixels for Training-free Segmentation

Faith and Fate: Limits of Transformers on Compositionality

Faster approximate subgraph counts with privacy

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering

SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization

Skill-it! A data-driven skills framework for understanding and training language models

Debiasing Pretrained Generative Models by Uniformly Sampling Semantic Attributes

Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition

ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling

StyleDrop: Text-to-Image Synthesis of Any Style

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

When Can We Track Significant Preference Shifts in Dueling Bandits?

H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets

Nash Regret Guarantees for Linear Bandits

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile

Robust low-rank training via approximate orthonormal constraints

GNeSF: Generalizable Neural Semantic Fields

Augmentation-Aware Self-Supervision for Data-Efficient GAN Training

MAViL: Masked Audio-Video Learners

A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm

Interpretable Graph Networks Formulate Universal Algebra Conjectures

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Self-Refine: Iterative Refinement with Self-Feedback

CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra

Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation

White-Box Transformers via Sparse Rate Reduction

4M: Massively Multimodal Masked Modeling

When can Regression-Adjusted Control Variate Help? Rare Events, Sobolev Embedding and Minimax Optimality

Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets

RDumb: A simple approach that questions our progress in continual test-time adaptation

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

RevColV2: Exploring Disentangled Representations in Masked Image Modeling

PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models

Making Scalable Meta Learning Practical

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models

MoVie: Visual Model-Based Policy Adaptation for View Generalization

Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

Leveraging the two-timescale regime to demonstrate convergence of neural networks

Training Chain-of-Thought via Latent-Variable Inference

Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter

Context-PIPs: Persistent Independent Particles Demands Spatial Context Features

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

ZipLM: Inference-Aware Structured Pruning of Language Models

Does a sparse ReLU network training problem always admit an optimum ?

Large Language Models of Code Fail at Completing Code with Potential Bugs

Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline

Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks

BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations

Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification

CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence

EvoPrompting: Language Models for Code-Level Neural Architecture Search

Near-Optimal Algorithms for Gaussians with Huber Contamination: Mean Estimation and Linear Regression

Ess-InfoGAIL: Semi-supervised Imitation Learning from Imbalanced Demonstrations

TextDiffuser: Diffusion Models as Text Painters

On permutation symmetries in Bayesian neural network posteriors: a variational perspective

Computing Optimal Nash Equilibria in Multiplayer Games

BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning

Fine-Grained Visual Prompting

Unconstrained Dynamic Regret via Sparse Coding

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

DiffComplete: Diffusion-based Generative 3D Shape Completion

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Individual Arbitrariness and Group Fairness

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

Explore In-Context Learning for 3D Point Cloud Understanding

Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning

StateMask: Explaining Deep Reinforcement Learning through State Mask

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Transformers learn through gradual rank increase

Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information

Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning

Weakly-Supervised Audio-Visual Segmentation

Retrieval-Augmented Multiple Instance Learning

Unsupervised Semantic Correspondence Using Stable Diffusion

Meta-in-context learning in large language models

Offline RL with Discrete Proxy Representations for Generalizability in POMDPs

Knowledge Distillation Performs Partial Variance Reduction

H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection

Exploiting Correlated Auxiliary Feedback in Parameterized Bandits

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

GAUCHE: A Library for Gaussian Processes in Chemistry

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

BayesDAG: Gradient-Based Posterior Inference for Causal Discovery

Optimal Algorithms for the Inhomogeneous Spiked Wigner Model

Error Discovery By Clustering Influence Embeddings

Quasi-Monte Carlo Graph Random Features

Operator Learning with Neural Fields: Tackling PDEs on General Geometries

Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization

AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Federated Multi-Objective Learning

A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings

Goal Driven Discovery of Distributional Differences via Language Descriptions

Counterfactual Generation with Identifiability Guarantees

CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation

ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection

Convex-Concave Zero-Sum Markov Stackelberg Games

Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics

Zeroth-Order Methods for Nondifferentiable, Nonconvex, and Hierarchical Federated Optimization

MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining

Causes and Effects of Unanticipated Numerical Deviations in Neural Network Inference Frameworks

Real-World Image Super-Resolution as Multi-Task Learning

ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers

Counterfactually Comparing Abstaining Classifiers

Koopman Kernel Regression

KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs

Achieving $\mathcal{O}(\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization

Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time

Lossy Image Compression with Conditional Diffusion Models

Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity

LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning

Regret Minimization via Saddle Point Optimization

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback

Experiment Planning with Function Approximation

Exploring Diverse In-Context Configurations for Image Captioning

Characterizing Out-of-Distribution Error via Optimal Transport

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images

Contextual Gaussian Process Bandits with Neural Networks

Labeling Neural Representations with Inverse Recognition

Coop: Memory is not a Commodity

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining

A Causal Framework for Decomposing Spurious Variations

PromptRestorer: A Prompting Image Restoration Method with Degradation Perception

Adversarial Counterfactual Environment Model Learning

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

Data Selection for Language Models via Importance Resampling

Linear Time Algorithms for k-means with Multi-Swap Local Search

Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes

Foundation Model is Efficient Multimodal Multitask Model Selector

Network Regression with Graph Laplacians

ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation

KuaiSim: A Comprehensive Simulator for Recommender Systems

Universality and Limitations of Prompt Tuning

[Re] Pure Noise to the Rescue of Insufficient Data

ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training

SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models

Scientific Document Retrieval using Multi-level Aspect-based Queries

Model Sparsity Can Simplify Machine Unlearning

Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets

Guide Your Agent with Adaptive Multimodal Rewards

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency

Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management

SwiFT: Swin 4D fMRI Transformer

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits

Sharp Spectral Rates for Koopman Operator Learning

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

MMD Aggregated Two-Sample Test

PopSign ASL v1.0: An Isolated American Sign Language Dataset Collected via Smartphones

Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild

Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker

A Diffusion-Model of Joint Interactive Navigation

The Pick-to-Learn Algorithm: Empowering Compression for Tight Generalization Bounds and Improved Post-training Performance

High Precision Causal Model Evaluation with Conditional Randomization

AVIS: Autonomous Visual Information Seeking with Large Language Model Agent

Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow Shrink Trees

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training

Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition

ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation

Percentile Criterion Optimization in Offline Reinforcement Learning

VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution

Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks

Switching Autoregressive Low-rank Tensor Models

Epidemic Learning: Boosting Decentralized Learning with Randomized Communication

Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model

SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection

Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach

Structured Neural-PI Control with End-to-End Stability and Output Tracking Guarantees

Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost

Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability

[Re] CrossWalk: Fairness-enhanced Node Representation Learning

Parallel Sampling of Diffusion Models

Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing

Temporal Causal Mediation through a Point Process: Direct and Indirect Effects of Healthcare Interventions

Reproducibility Study of ”Label-Free Explainability for Unsupervised Models”

Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data

MiliPoint: A Point Cloud Dataset for mmWave Radar

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

Survival Instinct in Offline Reinforcement Learning

Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

[Re] Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification

Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning

[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles

Reproducibility study of 'Proto2Proto: Can you recognise the car, the way I do?'

Euler-Lagrange Analysis of Generative Adversarial Networks

Energy Transformer

Neural Lighting Simulation for Urban Scenes

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

Prototypical Variational Autoencoder for 3D Few-shot Object Detection

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Strong and Precise Modulation of Human Percepts via Robustified ANNs

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

Regularizing Neural Networks with Meta-Learning Generative Models

Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning

Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs

[Re] Numerical influence of ReLU'(0) on backpropagation

AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity

Provably Safe Reinforcement Learning with Step-wise Violation Constraints

UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models

On Measuring Fairness in Generative Models

Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation

DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries

Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Dataset

PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation

[Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods

[Re] VAE Approximation Error: ELBO and Exponential Families

Reduced Policy Optimization for Continuous Control with Hard Constraints

Sampling weights of deep neural networks

Learning Interpretable Low-dimensional Representation via Physical Symmetry

Towards a fuller understanding of neurons with Clustered Compositional Explanations

Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection

Efficient Robust Bayesian Optimization for Arbitrary Uncertain inputs

Resilient Constrained Learning

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Pairwise Causality Guided Transformers for Event Sequences

An Iterative Self-Learning Framework for Medical Domain Generalization

Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment

RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency

Causal Discovery in Semi-Stationary Time Series

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

Extensible Prompts for Language Models on Zero-shot Language Style Customization

Switching Temporary Teachers for Semi-Supervised Semantic Segmentation

[Re] $\mathcal{G}$-Mixup: Graph Data Augmentation for Graph Classification

[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking

[Re] Variational Neural Cellular Automata

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

Equivariant Neural Operator Learning with Graphon Convolution

Effective Human-AI Teams via Learned Natural Language Rules and Onboarding

Easy Bayesian Transfer Learning with Informative Priors

Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds

ANPL: Towards Natural Programming with Interactive Decomposition

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models

Uncovering and Quantifying Social Biases in Code Generation

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer

Passive learning of active causal strategies in agents and language models

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation

SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models

An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions

Addressing Negative Transfer in Diffusion Models

Constant Approximation for Individual Preference Stable Clustering

LayoutPrompter: Awaken the Design Ability of Large Language Models

Structured Semidefinite Programming for Recovering Structured Preconditioners

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale

Change point detection and inference in multivariate non-parametric models under mixing conditions

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

GRAND-SLAMIN’ Interpretable Additive Modeling with Structural Constraints

The geometry of hidden representations of large transformer models

This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations

Stable Bias: Evaluating Societal Representations in Diffusion Models

Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

Parts of Speech–Grounded Subspaces in Vision-Language Models

Reproducibility Study of “Quantifying Societal Bias Amplification in Image Captioning”

Memory-Constrained Algorithms for Convex Optimization

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

Synthetic-to-Real Pose Estimation with Geometric Reconstruction

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control

Implicit Variational Inference for High-Dimensional Posteriors

Analyzing Generalization of Neural Networks through Loss Path Kernels

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

Auslan-Daily: Australian Sign Language Translation for Daily Communication and News

Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

Bifurcations and loss jumps in RNN training

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

Taylor TD-learning

State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory

Estimating Noise Correlations Across Continuous Conditions With Wishart Processes

Deep learning with kernels through RKHM and the Perron-Frobenius operator

Efficient Training of Energy-Based Models Using Jarzynski Equality

FABind: Fast and Accurate Protein-Ligand Binding

A Unified Conditional Framework for Diffusion-based Image Restoration

Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection

NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries

Double and Single Descent in Causal Inference with an Application to High-Dimensional Synthetic Control

Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective

Query-based Temporal Fusion with Explicit Motion for 3D Object Detection

On Masked Pre-training and the Marginal Likelihood

On Learning Necessary and Sufficient Causal Graphs

Learning List-Level Domain-Invariant Representations for Ranking

(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability

Goal-Conditioned Predictive Coding for Offline Reinforcement Learning

Diffused Redundancy in Pre-trained Representations

ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram

Adversarially Robust Learning with Uncertain Perturbation Sets

BayesTune: Bayesian Sparse Deep Model Fine-tuning

Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams

Rank-N-Contrast: Learning Continuous Representations for Regression

SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models

Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices

How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget

Rubik's Cube: High-Order Channel Interactions with a Hierarchical Receptive Field

Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

FouriDown: Factoring Down-Sampling into Shuffling and Superposing

Recasting Continual Learning as Sequence Modeling

LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP

Regularized Behavior Cloning for Blocking the Leakage of Past Action Information

Expressive Sign Equivariant Networks for Spectral Geometric Learning

AdANNS: A Framework for Adaptive Semantic Search

Continuous-time Analysis of Anchor Acceleration

Private Federated Frequency Estimation: Adapting to the Hardness of the Instance

Credal Marginal MAP

Canonical normalizing flows for manifold learning

QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules

Trial matching: capturing variability with data-constrained spiking neural networks

ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation

Learning Visual Prior via Generative Pre-Training

How Re-sampling Helps for Long-Tail Learning?

Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion

Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning

Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning

Mirror Diffusion Models for Constrained and Watermarked Generation

Template-free Articulated Neural Point Clouds for Reposable View Synthesis

Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes

Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice

XAGen: 3D Expressive Human Avatars Generation

NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos

Gradient Informed Proximal Policy Optimization

[Re] On the Reproducibility of CartoonX

[Re] Fairness Guarantees under Demographic Shift

Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start

OpenAGI: When LLM Meets Domain Experts

PRODIGY: Enabling In-context Learning Over Graphs

The Quantization Model of Neural Scaling

Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition

Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents

Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo

Mnemosyne: Learning to Train Transformers with Transformers

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

Flow Factorized Representation Learning

Zero-Shot Anomaly Detection via Batch Normalization

Sensitivity in Translation Averaging

Are GATs Out of Balance?

Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior

A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design

No-Regret Learning with Unbounded Losses: The Case of Logarithmic Pooling

Expanding Small-Scale Datasets with Guided Imagination

Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation

Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data

Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning

What Do Deep Saliency Models Learn about Visual Attention?

Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness

Combinatorial Group Testing with Selfish Agents

Domain Adaptive Imitation Learning with Visual Observation

Fast Attention Requires Bounded Entries

Adaptive Data Analysis in a Balanced Adversarial Model

Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations

A benchmark of categorical encoders for binary classification

Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates

Learning to Tokenize for Generative Retrieval

Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data

Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium

[Re] On Explainability of Graph Neural Networks via Subgraph Explorations

Sparse Graph Learning from Spatiotemporal Time Series

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

Synthcity: a benchmark framework for diverse use cases of tabular synthetic data

T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation

Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions

State Regularized Policy Optimization on Data with Dynamics Shift

Leveraging Locality and Robustness to Achieve Massively Scalable Gaussian Process Regression

GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER

A Variational Perspective on High-Resolution ODEs

Federated Learning via Meta-Variational Dropout

BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking

Interpretable Prototype-based Graph Information Bottleneck

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

Iteratively Learn Diverse Strategies with State Distance Information

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees

Temporal Continual Learning with Prior Compensation for Human Motion Prediction

[Re] On the Reproducibility of “FairCal: Fairness Calibration for Face Verification”

GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection

Statistically Valid Variable Importance Assessment through Conditional Permutations

Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning

Prompt-augmented Temporal Point Process for Streaming Event Sequence

Path following algorithms for $\ell_2$-regularized $M$-estimation with approximation guarantee

The CLIP Model is Secretly an Image-to-Prompt Converter

Finding Counterfactually Optimal Action Sequences in Continuous State Spaces

Maximum Independent Set: Self-Training through Dynamic Programming

Beyond Average Return in Markov Decision Processes

Stochastic Approximation Approaches to Group Distributionally Robust Optimization

Hierarchically Gated Recurrent Neural Network for Sequence Modeling

Graph Convolutional Kernel Machine versus Graph Convolutional Networks

Identification of Nonlinear Latent Hierarchical Models

Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing

A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference

Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection

Tracr: Compiled Transformers as a Laboratory for Interpretability

Proximity-Informed Calibration for Deep Neural Networks

RELIC: Reproducibility and Extension on LIC metric in quantifying bias in captioning models

[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints

AndroidInTheWild: A Large-Scale Dataset For Android Device Control

Preference-grounded Token-level Guidance for Language Model Fine-tuning

Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States

Designing Robust Transformers using Robust Kernel Density Estimation

Sample Complexity of Goal-Conditioned Hierarchical Reinforcement Learning

Towards Label Position Bias in Graph Neural Networks

Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization

Guiding Large Language Models via Directional Stimulus Prompting

CAST: Cross-Attention in Space and Time for Video Action Recognition

Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift

Do Not Marginalize Mechanisms, Rather Consolidate!

Cascading Contextual Assortment Bandits

Post Hoc Explanations of Language Models Can Improve Language Models

Likelihood Ratio Confidence Sets for Sequential Decision Making

HiBug: On Human-Interpretable Model Debug

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

Slow and Weak Attractor Computation Embedded in Fast and Strong E-I Balanced Neural Dynamics

Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference

Training Transitive and Commutative Multimodal Transformers with LoReTTa

QLoRA: Efficient Finetuning of Quantized LLMs

Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception

Unleashing the Power of Randomization in Auditing Differentially Private ML

Deep Reinforcement Learning with Plasticity Injection

Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond

[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization

Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis

Counterfactual Memorization in Neural Language Models

Importance-aware Co-teaching for Offline Model-based Optimization

Promises and Pitfalls of Threshold-based Auto-labeling

Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration

Graph-Structured Gaussian Processes for Transferable Graph Learning

Normalization Layers Are All That Sharpness-Aware Minimization Needs

Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations

Large sample spectral analysis of graph-based multi-manifold clustering

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments

AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator

RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization

Self-Evaluation Guided Beam Search for Reasoning

On the Identifiability of Sparse ICA without Assuming Non-Gaussianity

Imitation Learning from Imperfection: Theoretical Justifications and Algorithms

StableFDG: Style and Attention Based Learning for Federated Domain Generalization

ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation

Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

Optimizing Prompts for Text-to-Image Generation

Subject-driven Text-to-Image Generation via Apprenticeship Learning

BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction

Data Quality in Imitation Learning

Approximation-Generalization Trade-offs under (Approximate) Group Equivariance

Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer

Robust Learning with Progressive Data Expansion Against Spurious Correlation

Exploring and Interacting with the Set of Good Sparse Generalized Additive Models

ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets

Provably Bounding Neural Network Preimages

Into the LAION’s Den: Investigating Hate in Multimodal Datasets

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab

Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models

Explainable and Efficient Randomized Voting Rules

Mitigating Test-Time Bias for Fair Image Retrieval

Scaling Data-Constrained Language Models

Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies

Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean

Dynamic Non-monotone Submodular Maximization

Prediction and Control in Continual Reinforcement Learning

Bridging Discrete and Backpropagation: Straight-Through and Beyond

Diverse Community Data for Benchmarking Data Privacy Algorithms

DataPerf: Benchmarks for Data-Centric AI Development

Efficient Diffusion Policies For Offline Reinforcement Learning

Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network

Explore to Generalize in Zero-Shot RL

Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data

Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems

Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

Secure Out-of-Distribution Task Generalization with Energy-Based Models

Expressivity-Preserving GNN Simulation

An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization

BanditPAM++: Faster $k$-medoids Clustering

Most Neural Networks Are Almost Learnable

Estimating Generic 3D Room Structures from 2D Annotations

Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning

DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework

TOA: Task-oriented Active VQA

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

An Empirical Investigation of the Role of Pre-training in Lifelong Learning

BubbleML: A Multiphase Multiphysics Dataset and Benchmarks for Machine Learning

Task-aware Distributed Source Coding under Dynamic Bandwidth

Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning

Deep Equilibrium Based Neural Operators for Steady-State PDEs

Replicability in Reinforcement Learning

Have it your way: Individualized Privacy Assignment for DP-SGD

DICES Dataset: Diversity in Conversational AI Evaluation for Safety

DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization

Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach

Individualized Dosing Dynamics via Neural Eigen Decomposition

Structural Pruning for Diffusion Models

Joint Data-Task Generation for Auxiliary Learning

Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective

Meta-Learning Adversarial Bandit Algorithms

What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks

Exponentially Convergent Algorithms for Supervised Matrix Factorization

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers

Fundamental Limits and Tradeoffs in Invariant Representation Learning

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

Hyper-Skin: A Hyperspectral Dataset for Reconstructing Facial Skin-Spectra from RGB Images

Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics

Perception Test: A Diagnostic Benchmark for Multimodal Video Models

Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics

Diffusion Schrödinger Bridge Matching

Conformal PID Control for Time Series Prediction

Concentration analysis of multivariate elliptic diffusions

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy

Adversarial Model for Offline Reinforcement Learning

Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network

Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off

AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks

Sparse Deep Learning for Time Series Data: Theory and Applications

Large Language Models are Visual Reasoning Coordinators

Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Smooth Flipping Probability for Differential Private Sign Random Projection Methods

MADLAD-400: A Multilingual And Document-Level Large Audited Dataset

ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling

Self-supervised video pretraining yields robust and more human-aligned visual representations

Affinity-Aware Graph Networks

Towards Personalized Federated Learning via Heterogeneous Model Reassembly

Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis

Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction

Progressive Ensemble Distillation: Building Ensembles for Efficient Inference

Adaptive whitening with fast gain modulation and slow synaptic plasticity

MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues

A Logic for Expressing Log-Precision Transformers

The noise level in linear regression with dependent data

Lending Interaction Wings to Recommender Systems with Conversational Agents

Directional diffusion models for graph representation learning

Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond $1+\alpha$ Moments

Reining Generalization in Offline Reinforcement Learning via Representation Distinction

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

Structure of universal formulas

The Learnability of In-Context Learning

Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction

Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection

On Learning Latent Models with Multi-Instance Weak Supervision

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Customizable Image Synthesis with Multiple Subjects

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

Rethinking the Backward Propagation for Adversarial Transferability

Geometric Neural Diffusion Processes

SceneScape: Text-Driven Consistent Scene Generation

Task-Robust Pre-Training for Worst-Case Downstream Adaptation

Weighted ROC Curve in Cost Space: Extending AUC to Cost-Sensitive Learning

Low Tensor Rank Learning of Neural Dynamics

Alignment with human representations supports robust few-shot learning

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

Estimating Koopman operators with sketching to provably learn large scale dynamical systems

Transition-constant Normalization for Image Enhancement

Selective Sampling and Imitation Learning via Online Regression

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

NAS-X: Neural Adaptive Smoothing via Twisting

Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products

Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantisation.

Better Correlation and Robustness: A Distribution-Balanced Self-Supervised Learning Framework for Automatic Dialogue Evaluation

Learning to Compress Prompts with Gist Tokens

Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing

Small Transformers Compute Universal Metric Embeddings

Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics

The Separation Capacity of Random Neural Networks

Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data

Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds

Toolbox for Multimodal Learn (scikit-multimodallearn)

Graph Clustering with Graph Neural Networks

Reproducibility study of the Fairness-enhanced Node Representation Learning

Reproducibility Study of ”CartoonX: Cartoon Explanations of Image Classifiers”

A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes

Online Ad Procurement in Non-stationary Autobidding Worlds

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

VTaC: A Benchmark Dataset of Ventricular Tachycardia Alarms from ICU Monitors

TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning

Simple, Scalable and Effective Clustering via One-Dimensional Projections

The Distortion of Binomial Voting Defies Expectation

A Theory of Multimodal Learning

Robustness Guarantees for Adversarially Trained Neural Networks

TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

$H$-Consistency Bounds: Characterization and Extensions

GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation

Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization

Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

Langevin Quasi-Monte Carlo

Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand

CORL: Research-oriented Deep Offline Reinforcement Learning Library

Train 'n Trade: Foundations of Parameter Markets

Reproducibility Study of "Label-Free Explainability for Unsupervised Models"

What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding

Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs

Non-stationary Experimental Design under Linear Trends

Unbounded Differentially Private Quantile and Maximum Estimation

Sub-optimality of the Naive Mean Field approximation for proportional high-dimensional Linear Regression

Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels

Sheaf Hypergraph Networks

Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks

Improving the Knowledge Gradient Algorithm

Noise-Adaptive Thompson Sampling for Linear Contextual Bandits

Subspace Identification for Multi-Source Domain Adaptation

VeriX: Towards Verified Explainability of Deep Neural Networks

Uni3DETR: Unified 3D Detection Transformer

Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition

YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus

Scalable 3D Captioning with Pretrained Models

SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model