Fri 6:15 a.m. - 6:30 a.m.
|
Opening Remarks
(
Talk
)
>
SlidesLive Video
|
🔗
|
Fri 6:30 a.m. - 7:00 a.m.
|
Why should we care if humans and machines have similar representations?
(
Tom Griffiths Invited Talk
)
>
SlidesLive Video
|
🔗
|
Fri 7:00 a.m. - 7:30 a.m.
|
Symmetry and Universality
(
Sophia Sanborn Invited Talk
)
>
SlidesLive Video
|
🔗
|
Fri 7:30 a.m. - 8:00 a.m.
|
When representations align: Universality in representation learning dynamics
(
Andrew Saxe Invited Talk
)
>
SlidesLive Video
|
🔗
|
Fri 8:00 a.m. - 8:30 a.m.
|
Coffee break
|
🔗
|
Fri 8:30 a.m. - 9:45 a.m.
|
Contributed talks
(
Talks
)
>
SlidesLive Video
|
🔗
|
Fri 9:45 a.m. - 10:30 a.m.
|
Round Table
(
Discussion Panel
)
>
SlidesLive Video
|
🔗
|
Fri 10:30 a.m. - 11:45 a.m.
|
Lunch
|
🔗
|
Fri 11:45 a.m. - 12:15 p.m.
|
Local and global structure in neural network representations
(
Simon Kornblith Invited Talk
)
>
SlidesLive Video
|
🔗
|
Fri 12:15 p.m. - 12:45 p.m.
|
Reusing pretrained models for learning and unlearning tasks
(
Eleni Traintafillou Invited Talk
)
>
SlidesLive Video
|
🔗
|
Fri 12:45 p.m. - 1:15 p.m.
|
A rose by any other representation: some questions on the relationship between computation and representation
(
Andrew Lampinen Invited Talk
)
>
SlidesLive Video
|
🔗
|
Fri 1:15 p.m. - 3:15 p.m.
|
Poster session
(
Posters
)
>
SlidesLive Video
|
🔗
|
-
|
Characterizing pre-trained and task-adapted molecular representations
(
Poster
)
>
link
|
Celia Cintas · Payel Das · Jarret Ross · Brian Belgodere · Girmaw Abebe Tadesse · Vijil Chenthamarakshan · Jannis Born · Skyler D. Speakman
🔗
|
-
|
Duality of Bures and Shape Distances with Implications for Comparing Neural Representations
(
Poster
)
>
link
|
Sarah Harvey · Brett Larsen · Alex Williams
🔗
|
-
|
WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability
(
Poster
)
>
link
|
Yufan Zhuang · Zihan Wang · Fangbo Tao · Jingbo Shang
🔗
|
-
|
NEUCORE: Neural Concept Reasoning for Composed Image Retrieval
(
Poster
)
>
link
|
Shu Zhao · Huijuan Xu
🔗
|
-
|
Grokking as Simplification: A Nonlinear Complexity Perspective
(
Poster
)
>
link
|
Ziming Liu · Ziqian Zhong · Max Tegmark
🔗
|
-
|
Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
(
Poster
)
>
link
|
Marvin Schmitt · Daniel Habermann · Paul-Christian Bürkner · Ullrich Köthe · Stefan Radev
🔗
|
-
|
Efficient Multimodal Alignment: To Freeze or Not to Freeze?
(
Poster
)
>
link
|
Till Aczel · Roger Wattenhofer
🔗
|
-
|
What Does Knowledge Distillation Distill?
(
Poster
)
>
link
|
Cindy Wu · Ekdeep S Lubana · Bruno Mlodozeniec · Robert Kirk · David Krueger
🔗
|
-
|
Comparing Representational and Functional Similarity in Small Transformer Language Models
(
Poster
)
>
link
|
Dan Friedman · Andrew Lampinen · Lucas Dixon · Danqi Chen · Asma Ghandeharioun
🔗
|
-
|
Representational constraints underlying similarity between task-optimized neural systems
(
Poster
)
>
link
|
Tahereh Toosi
🔗
|
-
|
A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry
(
Poster
)
>
link
|
Tim Xiao · Weiyang Liu · Robert Bamler
🔗
|
-
|
ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development
(
Poster
)
>
link
|
Benjamin Cappell · Andreas Stoll · Chukwudi Umah · Bernhard Egger
🔗
|
-
|
Multimodal decoding of human brain activity into images and text
(
Poster
)
>
link
|
Matteo Ferrante · Tommaso Boccato · Furkan Ozcelik · Rufin VanRullen · Nicola Toschi
🔗
|
-
|
Predictive variational autoencoder for learning robust representations of time-series data
(
Poster
)
>
link
|
Julia Wang · Dexter Tsin · Tatiana Engel
🔗
|
-
|
Instruction-tuned LLMs with World Knowledge are More Aligned to the Human Brain
(
Poster
)
>
link
|
Khai Loong Aw · Syrielle Montariol · Badr AlKhamissi · Martin Schrimpf · Antoine Bosselut
🔗
|
-
|
On Transferring Expert Knowledge from Tabular Data to Images
(
Poster
)
>
link
|
Jun-Peng Jiang · Han-Jia Ye · Leye Wang · Yang Yang · Yuan Jiang · De-Chuan Zhan
🔗
|
-
|
On the Robustness of Neural Collapse and the Neural Collapse of Robustness
(
Poster
)
>
link
|
Jingtong Su · Ya Shi Zhang · Nikolaos Tsilivis · Julia Kempe
🔗
|
-
|
MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation
(
Poster
)
>
link
|
Muhammad Osama Khan · Junbang Liang · Chun-Kai Wang · Shan Yang · Yu Lou
🔗
|
-
|
Linearly Structured World Representations in Maze-Solving Transformers
(
Poster
)
>
link
|
12 presenters
Michael Ivanitskiy · Alexander Spies · Tilman Räuker · Guillaume Corlouer · Christopher Mathwin · Lucia Quirke · Can Rager · Rusheb Shah · Dan Valentine · Cecilia Diniz Behn · Katsumi Inoue · Samy Wu Fung
🔗
|
-
|
A General Method for Testing Bayesian Models using Neural Data
(
Poster
)
>
link
|
Gabor Lengyel · Sabyasachi Shivkumar · Ralf Haefner
🔗
|
-
|
ZipIt!: Multitask Model Merging without Training
(
Poster
)
>
link
|
George Stoica · Daniel Bolya · Jakob Bjorner · Pratik Ramesh · Taylor Hearn · Judy Hoffman
🔗
|
-
|
Degradation and plasticity in convolutional neural networks: An investigation of internal representations
(
Poster
)
>
link
|
Jasmine Moore · Vibujithan Vigneshwaran · Matthias Wilms · Nils Daniel Forkert
🔗
|
-
|
On the Direct Alignment of Latent Spaces
(
Poster
)
>
link
|
Zorah Lähner · Michael Moeller
🔗
|
-
|
Reinforcement Learning with Augmentation Invariant Representation: A Non-contrastive Approach
(
Poster
)
>
link
|
Nasik Muhammad Nafi · William Hsu
🔗
|
-
|
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
(
Poster
)
>
link
|
Haoxiang Wang · Pavan Kumar Anasosalu Vasu · Fartash Faghri · Raviteja Vemulapalli · Mehrdad Farajtabar · Sachin Mehta · Mohammad Rastegari · Oncel Tuzel · Hadi Pouransari
🔗
|
-
|
Comparing neural models using their perceptual discriminability predictions
(
Poster
)
>
link
|
Jingyang Zhou · Chanwoo Chun · Ajay Subramanian · Eero Simoncelli
🔗
|
-
|
Semi-Ensemble: A Simple Approach Over-parameterize Model Interpolation
(
Poster
)
>
link
|
Jiwoon Lee · Jaeho Lee
🔗
|
-
|
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement
(
Poster
)
>
link
|
Mohammadreza (Reza) Salehi · Mehrdad Farajtabar · Maxwell Horton · Fartash Faghri · Hadi Pouransari · Raviteja Vemulapalli · Oncel Tuzel · Ali Farhadi · Mohammad Rastegari · Sachin Mehta
🔗
|
-
|
Understanding Learning Dynamics of Neural Representations via Feature Visualization at Scale
(
Poster
)
>
link
|
Chandana Kuntala · Deepak Sharma · Carlos Ponce · Binxu Wang
🔗
|
-
|
Unsupervised learning on spontaneous retinal activity leads to efficient neural representation geometry
(
Poster
)
>
link
|
Andrew Ligeralde · Yilun Kuang · Thomas Yerxa · Miah Pitcher · Marla Feller · SueYeon Chung
🔗
|
-
|
Estimating shape distances on neural representations with limited samples
(
Poster
)
>
link
|
Dean Pospisil · Brett Larsen · Sarah Harvey · Alex Williams
🔗
|
-
|
Growing Brains: Co-emergence of Anatomical and Functional Modularity in Recurrent Neural Networks
(
Poster
)
>
link
|
Ziming Liu · Mikail Khona · Ila Fiete · Max Tegmark
🔗
|
-
|
Towards Measuring Representational Similarity of Large Language Models
(
Poster
)
>
link
|
Max Klabunde · Mehdi Ben Amor · Michael Granitzer · Florian Lemmerich
🔗
|
-
|
Bio-inspired parameter reuse: Exploiting inter-frame representation similarity with recurrence for accelerating temporal visual processing
(
Poster
)
>
link
|
Zuowen Wang · Longbiao Cheng · Joachim Ott · Pehuen Moure · Shih-Chii Liu
🔗
|
-
|
UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification
(
Poster
)
>
link
|
Jennifer Crawford · Haoli Yin · Luke McDermott · Daniel Cummings
🔗
|
-
|
Testing Assumptions Underlying a Unified Theory for the Origin of Grid Cells
(
Poster
)
>
link
|
Rylan Schaeffer · Mikail Khona · Adrian Bertagnoli · Sanmi Koyejo · Ila Fiete
🔗
|
-
|
Understanding Mode Connectivity via Parameter Space Symmetry
(
Poster
)
>
link
|
Bo Zhao · Nima Dehmamy · Robin Walters · Rose Yu
🔗
|
-
|
Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words
(
Poster
)
>
link
|
Yujia Bao · Srinivasan Sivanandan · Theofanis Karaletsos
🔗
|
-
|
DisCoV: Disentangling Time Series Representations via Contrastive based $l$-Variational Inference
(
Poster
)
>
link
|
Khalid OUBLAL · Said Ladjal · David Benhaiem · Emmanuel LE BORGNE · François Roueff
🔗
|
-
|
Mixture of Multimodal Interaction Experts
(
Poster
)
>
link
|
Haofei Yu · Paul Pu Liang · Russ Salakhutdinov · Louis-Philippe Morency
🔗
|
-
|
Inverted-Attention Transformers can Learn Object Representations: Insights from Slot Attention
(
Poster
)
>
link
|
Yi-Fu Wu · Klaus Greff · Gamaleldin Elsayed · Michael Mozer · Thomas Kipf · Sjoerd van Steenkiste
🔗
|
-
|
Increasing Brain-LLM Alignment via Information-Theoretic Compression
(
Poster
)
>
link
|
Mycal Tucker · Greta Tuckute
🔗
|
-
|
NoPose-NeuS: Jointly Optimizing Camera Poses with Neural Implicit Surfaces for Multi-view Reconstruction
(
Poster
)
>
link
|
Mohamed Sabae · Hoda Baraka · Mayada Hadhoud
🔗
|
-
|
Functional Modularity in Mind and Machine
(
Poster
)
>
link
|
Devon Jarvis · Richard Klein · Benjamin Rosman · Andrew Saxe
🔗
|
-
|
Are Spiking Neural Networks more expressive than Artificial Neural Networks?
(
Poster
)
>
link
|
Manjot Singh · Adalbert Fono · Gitta Kutyniok
🔗
|
-
|
Disentangling Linear Mode Connectivity
(
Poster
)
>
link
|
Gül Sena Altıntaş · Gregor Bachmann · Lorenzo Noci · Thomas Hofmann
🔗
|
-
|
Model Merging by Gradient Matching
(
Poster
)
>
link
|
Nico Daheim · Thomas Möllenhoff · Edoardo Maria Ponti · Iryna Gurevych · Mohammad Emtiyaz Khan
🔗
|
-
|
Object-Centric Semantic Vector Quantization
(
Poster
)
>
link
|
Yi-Fu Wu · Minseung Lee · Sungjin Ahn
🔗
|
-
|
Evaluation of Representational Similarity Scores Across Human Visual Cortex
(
Poster
)
>
link
|
Francisco Acosta · Colin Conwell · David Klindt · Nina Miolane
🔗
|
-
|
Supervising Variational Autoencoder Latent Representations with Language
(
Poster
)
>
link
|
Thomas Lu · Aboli Marathe · Ada Martin
🔗
|
-
|
Implicit Representations for Image Segmentation
(
Poster
)
>
link
|
Jan Philipp Schneider · Mishal Fatima · Jovita Lukasik · Andreas Kolb · Margret Keuper · Michael Moeller
🔗
|
-
|
Ecological data and objectives align deep neural network representations with humans
(
Poster
)
>
link
|
Akash Nagaraj · Alekh Karkada Ashok · Drew Linsley · Francis Lewis · Peisen Zhou · Thomas Serre
🔗
|
-
|
Visual Expertise Explains Image Inversion Effects
(
Poster
)
>
link
|
Martha Gahl · Shubham Kulkarni · Nikhil Pathak · Alex Russell · Gary Cottrell
🔗
|
-
|
How Good is a Single Basin?
(
Poster
)
>
link
|
Kai Lion · Gregor Bachmann · Lorenzo Noci · Thomas Hofmann
🔗
|
-
|
Subjective Randomness and In-Context Learning
(
Poster
)
>
link
|
Eric Bigelow · Ekdeep S Lubana · Robert Dick · Hidenori Tanaka · Tomer Ullman
🔗
|
-
|
Deep Multimodal Emotion Recognition using Modality Aware Attention Network for Unifying Representations in Neural Models
(
Poster
)
>
link
|
Sungpil Woo · MUHAMMAD ZUBAIR · Sunhwan Lim · Daeyoung Kim
🔗
|
-
|
On Feature Learning of Recursive Feature Machines and Automatic Relevance Determination
(
Poster
)
>
link
|
Daniel Gedon · Amirhesam Abedsoltan · Thomas Schön · Misha Belkin
🔗
|
-
|
Revisiting Supervision for Continual Representation Learning
(
Poster
)
>
link
|
Daniel Marczak · Sebastian Cygert · Tomasz Trzcinski · Bartłomiej Twardowski
🔗
|
-
|
Role Taxonomy of Units in Deep Neural Networks
(
Poster
)
>
link
|
Yang Zhao · Hao Zhang · Xiuyuan Hu
🔗
|
-
|
A sparse null code emerges in deep neural networks
(
Poster
)
>
link
|
Brian Robinson · Nathan Drenkow · Colin Conwell · Michael Bonner
🔗
|
-
|
How does fine-tuning affect your model? Mechanistic analysis on procedural tasks
(
Poster
)
>
link
|
Samyak Jain · Robert Kirk · Ekdeep S Lubana · Robert Dick · Hidenori Tanaka · Tim Rocktäschel · Edward Grefenstette · David Krueger
🔗
|
-
|
Variational Classification
(
Poster
)
>
link
|
Shehzaad Dhuliawala · Mrinmaya Sachan · Carl Allen
🔗
|
-
|
Hybrid Early Fusion for Multi-Modal Biomedical Representations
(
Poster
)
>
link
|
Konstantin Hemker · Nikola Simidjievski · Mateja Jamnik
🔗
|
-
|
Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
(
Poster
)
>
link
|
Jinyung Hong · Theodore P. Pavlic
🔗
|
-
|
Linear Mode Connectivity in Sparse Neural Networks
(
Poster
)
>
link
|
Luke McDermott · Daniel Cummings
🔗
|
-
|
SimVAE: Narrowing the gap between Discriminative & Generative Representation Learning
(
Poster
)
>
link
|
Alice Bizeul · Carl Allen
🔗
|
-
|
Distributional Reinforcement Learning in the Mammalian Brain
(
Poster
)
>
link
|
Adam Lowet · Qiao Zheng · Melissa Meng · Sara Matias · Jan Drugowitsch · Naoshige Uchida
🔗
|
-
|
Soft Matching Distance: A metric on neural representations that captures single-neuron tuning
(
Poster
)
>
link
|
Meenakshi Khosla · Alex Williams
🔗
|
-
|
Universality of intrinsic dimension of latent representations across models
(
Poster
)
>
link
|
Teresa Scheidt · Lars Kai Hansen
🔗
|
-
|
On consequences of finetuning on data with highly discriminative features
(
Poster
)
>
link
|
Wojciech Masarczyk · Tomasz Trzcinski · Mateusz Ostaszewski
🔗
|
-
|
An Information-Theoretic Understanding of Maximum Manifold Capacity Representations
(
Poster
)
>
link
|
Berivan Isik · Victor Lecomte · Rylan Schaeffer · Yann LeCun · Mikail Khona · Ravid Shwartz-Ziv · Sanmi Koyejo · Andrey Gromov
🔗
|
-
|
SHARCS: Shared Concept Space for\\Explainable Multimodal Learning
(
Poster
)
>
link
|
Gabriele Dominici · Pietro Barbiero · Lucie Charlotte Magister · Pietro Lió · Nikola Simidjievski
🔗
|
-
|
Sufficient conditions for offline reactivation in recurrent neural networks
(
Poster
)
>
link
|
Nanda H Krishna · Colin Bredenberg · Daniel Levenstein · Blake Richards · Guillaume Lajoie
🔗
|
-
|
On the universality of neural codes in vision
(
Poster
)
>
link
|
Florentin Guth · Brice Ménard
🔗
|
-
|
Event-Based Contrastive Learning for Medical Time Series
(
Poster
)
>
link
|
Hyewon Jeong · Nassim Oufattole · Aparna Balagopalan · Matthew McDermott · Payal Chandak · Marzyeh Ghassemi · Collin Stultz
🔗
|
-
|
Multi-timescale reinforcement learning in the brain
(
Poster
)
>
link
|
Paul Masset · Pablo Tano · HyungGoo Kim · Athar Malik · Alexandre Pouget · Naoshige Uchida
🔗
|
-
|
Duality of Bures and Shape Distances with Implications for Comparing Neural Representations
(
Spotlight
)
>
link
SlidesLive Video
|
Sarah Harvey · Brett Larsen · Alex Williams
🔗
|
-
|
ZipIt!: Multitask Model Merging without Training
(
Spotlight
)
>
link
SlidesLive Video
|
George Stoica · Daniel Bolya · Jakob Bjorner · Pratik Ramesh · Taylor Hearn · Judy Hoffman
🔗
|
-
|
Are Spiking Neural Networks more expressive than Artificial Neural Networks?
(
Spotlight
)
>
link
SlidesLive Video
|
Manjot Singh · Adalbert Fono · Gitta Kutyniok
🔗
|
-
|
A sparse null code emerges in deep neural networks
(
Spotlight
)
>
link
SlidesLive Video
|
Brian Robinson · Nathan Drenkow · Colin Conwell · Michael Bonner
🔗
|
-
|
Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
(
Spotlight
)
>
link
SlidesLive Video
|
Jinyung Hong · Theodore P. Pavlic
🔗
|
-
|
Distributional Reinforcement Learning in the Mammalian Brain
(
Spotlight
)
>
link
SlidesLive Video
|
Adam Lowet · Qiao Zheng · Melissa Meng · Sara Matias · Jan Drugowitsch · Naoshige Uchida
🔗
|
-
|
Soft Matching Distance: A metric on neural representations that captures single-neuron tuning
(
Spotlight
)
>
link
SlidesLive Video
|
Meenakshi Khosla · Alex Williams
🔗
|
-
|
An Information-Theoretic Understanding of Maximum Manifold Capacity Representations
(
Spotlight
)
>
link
SlidesLive Video
|
Berivan Isik · Victor Lecomte · Rylan Schaeffer · Yann LeCun · Mikail Khona · Ravid Shwartz-Ziv · Sanmi Koyejo · Andrey Gromov
🔗
|
-
|
Characterizing pre-trained and task-adapted molecular representations
(
Spotlight
)
>
link
|
Celia Cintas · Payel Das · Jarret Ross · Brian Belgodere · Girmaw Abebe Tadesse · Vijil Chenthamarakshan · Jannis Born · Skyler D. Speakman
🔗
|
-
|
WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability
(
Spotlight
)
>
link
SlidesLive Video
|
Yufan Zhuang · Zihan Wang · Fangbo Tao · Jingbo Shang
🔗
|
-
|
NEUCORE: Neural Concept Reasoning for Composed Image Retrieval
(
Spotlight
)
>
link
SlidesLive Video
|
Shu Zhao · Huijuan Xu
🔗
|
-
|
Grokking as Simplification: A Nonlinear Complexity Perspective
(
Spotlight
)
>
link
|
Ziming Liu · Ziqian Zhong · Max Tegmark
🔗
|
-
|
Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
(
Spotlight
)
>
link
SlidesLive Video
|
Marvin Schmitt · Daniel Habermann · Paul-Christian Bürkner · Ullrich Köthe · Stefan Radev
🔗
|
-
|
Efficient Multimodal Alignment: To Freeze or Not to Freeze?
(
Spotlight
)
>
link
|
Till Aczel · Roger Wattenhofer
🔗
|
-
|
What Does Knowledge Distillation Distill?
(
Spotlight
)
>
link
|
Cindy Wu · Ekdeep S Lubana · Bruno Mlodozeniec · Robert Kirk · David Krueger
🔗
|
-
|
Comparing Representational and Functional Similarity in Small Transformer Language Models
(
Spotlight
)
>
link
|
Dan Friedman · Andrew Lampinen · Lucas Dixon · Danqi Chen · Asma Ghandeharioun
🔗
|
-
|
Representational constraints underlying similarity between task-optimized neural systems
(
Spotlight
)
>
link
|
Tahereh Toosi
🔗
|
-
|
A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry
(
Spotlight
)
>
link
SlidesLive Video
|
Tim Xiao · Weiyang Liu · Robert Bamler
🔗
|
-
|
ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development
(
Spotlight
)
>
link
SlidesLive Video
|
Benjamin Cappell · Andreas Stoll · Chukwudi Umah · Bernhard Egger
🔗
|
-
|
Multimodal decoding of human brain activity into images and text
(
Spotlight
)
>
link
SlidesLive Video
|
Matteo Ferrante · Tommaso Boccato · Furkan Ozcelik · Rufin VanRullen · Nicola Toschi
🔗
|
-
|
Predictive variational autoencoder for learning robust representations of time-series data
(
Spotlight
)
>
link
|
Julia Wang · Dexter Tsin · Tatiana Engel
🔗
|
-
|
Instruction-tuned LLMs with World Knowledge are More Aligned to the Human Brain
(
Spotlight
)
>
link
SlidesLive Video
|
Khai Loong Aw · Syrielle Montariol · Badr AlKhamissi · Martin Schrimpf · Antoine Bosselut
🔗
|
-
|
On Transferring Expert Knowledge from Tabular Data to Images
(
Spotlight
)
>
link
SlidesLive Video
|
Jun-Peng Jiang · Han-Jia Ye · Leye Wang · Yang Yang · Yuan Jiang · De-Chuan Zhan
🔗
|
-
|
On the Robustness of Neural Collapse and the Neural Collapse of Robustness
(
Spotlight
)
>
link
|
Jingtong Su · Ya Shi Zhang · Nikolaos Tsilivis · Julia Kempe
🔗
|
-
|
MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation
(
Spotlight
)
>
link
|
Muhammad Osama Khan · Junbang Liang · Chun-Kai Wang · Shan Yang · Yu Lou
🔗
|
-
|
Linearly Structured World Representations in Maze-Solving Transformers
(
Spotlight
)
>
link
|
12 presenters
Michael Ivanitskiy · Alexander Spies · Tilman Räuker · Guillaume Corlouer · Christopher Mathwin · Lucia Quirke · Can Rager · Rusheb Shah · Dan Valentine · Cecilia Diniz Behn · Katsumi Inoue · Samy Wu Fung
🔗
|
-
|
A General Method for Testing Bayesian Models using Neural Data
(
Spotlight
)
>
link
SlidesLive Video
|
Gabor Lengyel · Sabyasachi Shivkumar · Ralf Haefner
🔗
|
-
|
Degradation and plasticity in convolutional neural networks: An investigation of internal representations
(
Spotlight
)
>
link
|
Jasmine Moore · Vibujithan Vigneshwaran · Matthias Wilms · Nils Daniel Forkert
🔗
|
-
|
On the Direct Alignment of Latent Spaces
(
Spotlight
)
>
link
|
Zorah Lähner · Michael Moeller
🔗
|
-
|
Reinforcement Learning with Augmentation Invariant Representation: A Non-contrastive Approach
(
Spotlight
)
>
link
|
Nasik Muhammad Nafi · William Hsu
🔗
|
-
|
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
(
Spotlight
)
>
link
|
Haoxiang Wang · Pavan Kumar Anasosalu Vasu · Fartash Faghri · Raviteja Vemulapalli · Mehrdad Farajtabar · Sachin Mehta · Mohammad Rastegari · Oncel Tuzel · Hadi Pouransari
🔗
|
-
|
Comparing neural models using their perceptual discriminability predictions
(
Spotlight
)
>
link
|
Jingyang Zhou · Chanwoo Chun · Ajay Subramanian · Eero Simoncelli
🔗
|
-
|
Semi-Ensemble: A Simple Approach Over-parameterize Model Interpolation
(
Spotlight
)
>
link
SlidesLive Video
|
Jiwoon Lee · Jaeho Lee
🔗
|
-
|
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement
(
Spotlight
)
>
link
|
Mohammadreza (Reza) Salehi · Mehrdad Farajtabar · Maxwell Horton · Fartash Faghri · Hadi Pouransari · Raviteja Vemulapalli · Oncel Tuzel · Ali Farhadi · Mohammad Rastegari · Sachin Mehta
🔗
|
-
|
Understanding Learning Dynamics of Neural Representations via Feature Visualization at Scale
(
Spotlight
)
>
link
SlidesLive Video
|
Chandana Kuntala · Deepak Sharma · Carlos Ponce · Binxu Wang
🔗
|
-
|
Unsupervised learning on spontaneous retinal activity leads to efficient neural representation geometry
(
Spotlight
)
>
link
|
Andrew Ligeralde · Yilun Kuang · Thomas Yerxa · Miah Pitcher · Marla Feller · SueYeon Chung
🔗
|
-
|
Estimating shape distances on neural representations with limited samples
(
Spotlight
)
>
link
|
Dean Pospisil · Brett Larsen · Sarah Harvey · Alex Williams
🔗
|
-
|
Growing Brains: Co-emergence of Anatomical and Functional Modularity in Recurrent Neural Networks
(
Spotlight
)
>
link
|
Ziming Liu · Mikail Khona · Ila Fiete · Max Tegmark
🔗
|
-
|
Towards Measuring Representational Similarity of Large Language Models
(
Spotlight
)
>
link
SlidesLive Video
|
Max Klabunde · Mehdi Ben Amor · Michael Granitzer · Florian Lemmerich
🔗
|
-
|
Bio-inspired parameter reuse: Exploiting inter-frame representation similarity with recurrence for accelerating temporal visual processing
(
Spotlight
)
>
link
|
Zuowen Wang · Longbiao Cheng · Joachim Ott · Pehuen Moure · Shih-Chii Liu
🔗
|
-
|
UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification
(
Spotlight
)
>
link
|
Jennifer Crawford · Haoli Yin · Luke McDermott · Daniel Cummings
🔗
|
-
|
Testing Assumptions Underlying a Unified Theory for the Origin of Grid Cells
(
Spotlight
)
>
link
SlidesLive Video
|
Rylan Schaeffer · Mikail Khona · Adrian Bertagnoli · Sanmi Koyejo · Ila Fiete
🔗
|
-
|
Understanding Mode Connectivity via Parameter Space Symmetry
(
Spotlight
)
>
link
|
Bo Zhao · Nima Dehmamy · Robin Walters · Rose Yu
🔗
|
-
|
Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words
(
Spotlight
)
>
link
SlidesLive Video
|
Yujia Bao · Srinivasan Sivanandan · Theofanis Karaletsos
🔗
|
-
|
DisCoV: Disentangling Time Series Representations via Contrastive based $l$-Variational Inference
(
Spotlight
)
>
link
|
Khalid OUBLAL · Said Ladjal · David Benhaiem · Emmanuel LE BORGNE · François Roueff
🔗
|
-
|
Mixture of Multimodal Interaction Experts
(
Spotlight
)
>
link
|
Haofei Yu · Paul Pu Liang · Russ Salakhutdinov · Louis-Philippe Morency
🔗
|
-
|
Inverted-Attention Transformers can Learn Object Representations: Insights from Slot Attention
(
Spotlight
)
>
link
|
Yi-Fu Wu · Klaus Greff · Gamaleldin Elsayed · Michael Mozer · Thomas Kipf · Sjoerd van Steenkiste
🔗
|
-
|
Increasing Brain-LLM Alignment via Information-Theoretic Compression
(
Spotlight
)
>
link
SlidesLive Video
|
Mycal Tucker · Greta Tuckute
🔗
|
-
|
NoPose-NeuS: Jointly Optimizing Camera Poses with Neural Implicit Surfaces for Multi-view Reconstruction
(
Spotlight
)
>
link
SlidesLive Video
|
Mohamed Sabae · Hoda Baraka · Mayada Hadhoud
🔗
|
-
|
Functional Modularity in Mind and Machine
(
Spotlight
)
>
link
|
Devon Jarvis · Richard Klein · Benjamin Rosman · Andrew Saxe
🔗
|
-
|
Disentangling Linear Mode Connectivity
(
Spotlight
)
>
link
|
Gül Sena Altıntaş · Gregor Bachmann · Lorenzo Noci · Thomas Hofmann
🔗
|
-
|
Model Merging by Gradient Matching
(
Spotlight
)
>
link
|
Nico Daheim · Thomas Möllenhoff · Edoardo Maria Ponti · Iryna Gurevych · Mohammad Emtiyaz Khan
🔗
|
-
|
Object-Centric Semantic Vector Quantization
(
Spotlight
)
>
link
|
Yi-Fu Wu · Minseung Lee · Sungjin Ahn
🔗
|
-
|
Evaluation of Representational Similarity Scores Across Human Visual Cortex
(
Spotlight
)
>
link
|
Francisco Acosta · Colin Conwell · David Klindt · Nina Miolane
🔗
|
-
|
Supervising Variational Autoencoder Latent Representations with Language
(
Spotlight
)
>
link
SlidesLive Video
|
Thomas Lu · Aboli Marathe · Ada Martin
🔗
|
-
|
Implicit Representations for Image Segmentation
(
Spotlight
)
>
link
|
Jan Philipp Schneider · Mishal Fatima · Jovita Lukasik · Andreas Kolb · Margret Keuper · Michael Moeller
🔗
|
-
|
Ecological data and objectives align deep neural network representations with humans
(
Spotlight
)
>
link
|
Akash Nagaraj · Alekh Karkada Ashok · Drew Linsley · Francis Lewis · Peisen Zhou · Thomas Serre
🔗
|
-
|
Visual Expertise Explains Image Inversion Effects
(
Spotlight
)
>
link
|
Martha Gahl · Shubham Kulkarni · Nikhil Pathak · Alex Russell · Gary Cottrell
🔗
|
-
|
How Good is a Single Basin?
(
Spotlight
)
>
link
|
Kai Lion · Gregor Bachmann · Lorenzo Noci · Thomas Hofmann
🔗
|
-
|
Subjective Randomness and In-Context Learning
(
Spotlight
)
>
link
|
Eric Bigelow · Ekdeep S Lubana · Robert Dick · Hidenori Tanaka · Tomer Ullman
🔗
|
-
|
Deep Multimodal Emotion Recognition using Modality Aware Attention Network for Unifying Representations in Neural Models
(
Spotlight
)
>
link
|
Sungpil Woo · MUHAMMAD ZUBAIR · Sunhwan Lim · Daeyoung Kim
🔗
|
-
|
On Feature Learning of Recursive Feature Machines and Automatic Relevance Determination
(
Spotlight
)
>
link
|
Daniel Gedon · Amirhesam Abedsoltan · Thomas Schön · Misha Belkin
🔗
|
-
|
Revisiting Supervision for Continual Representation Learning
(
Spotlight
)
>
link
|
Daniel Marczak · Sebastian Cygert · Tomasz Trzcinski · Bartłomiej Twardowski
🔗
|
-
|
Role Taxonomy of Units in Deep Neural Networks
(
Spotlight
)
>
link
|
Yang Zhao · Hao Zhang · Xiuyuan Hu
🔗
|
-
|
How does fine-tuning affect your model? Mechanistic analysis on procedural tasks
(
Spotlight
)
>
link
|
Samyak Jain · Robert Kirk · Ekdeep S Lubana · Robert Dick · Hidenori Tanaka · Tim Rocktäschel · Edward Grefenstette · David Krueger
🔗
|
-
|
Variational Classification
(
Spotlight
)
>
link
|
Shehzaad Dhuliawala · Mrinmaya Sachan · Carl Allen
🔗
|
-
|
Hybrid Early Fusion for Multi-Modal Biomedical Representations
(
Spotlight
)
>
link
|
Konstantin Hemker · Nikola Simidjievski · Mateja Jamnik
🔗
|
-
|
Linear Mode Connectivity in Sparse Neural Networks
(
Spotlight
)
>
link
|
Luke McDermott · Daniel Cummings
🔗
|
-
|
SimVAE: Narrowing the gap between Discriminative & Generative Representation Learning
(
Spotlight
)
>
link
|
Alice Bizeul · Carl Allen
🔗
|
-
|
Universality of intrinsic dimension of latent representations across models
(
Spotlight
)
>
link
|
Teresa Scheidt · Lars Kai Hansen
🔗
|
-
|
On consequences of finetuning on data with highly discriminative features
(
Spotlight
)
>
link
|
Wojciech Masarczyk · Tomasz Trzcinski · Mateusz Ostaszewski
🔗
|
-
|
SHARCS: Shared Concept Space for\\Explainable Multimodal Learning
(
Spotlight
)
>
link
SlidesLive Video
|
Gabriele Dominici · Pietro Barbiero · Lucie Charlotte Magister · Pietro Lió · Nikola Simidjievski
🔗
|
-
|
Sufficient conditions for offline reactivation in recurrent neural networks
(
Spotlight
)
>
link
|
Nanda H Krishna · Colin Bredenberg · Daniel Levenstein · Blake Richards · Guillaume Lajoie
🔗
|
-
|
On the universality of neural codes in vision
(
Spotlight
)
>
link
|
Florentin Guth · Brice Ménard
🔗
|
-
|
Event-Based Contrastive Learning for Medical Time Series
(
Spotlight
)
>
link
SlidesLive Video
|
Hyewon Jeong · Nassim Oufattole · Aparna Balagopalan · Matthew McDermott · Payal Chandak · Marzyeh Ghassemi · Collin Stultz
🔗
|
-
|
Multi-timescale reinforcement learning in the brain
(
Spotlight
)
>
link
|
Paul Masset · Pablo Tano · HyungGoo Kim · Athar Malik · Alexandre Pouget · Naoshige Uchida
🔗
|