Sat 6:45 a.m. - 7:00 a.m.
|
Opening Remarks
(
Introduction
)
>
SlidesLive Video
|
Ian Mason
🔗
|
Sat 7:00 a.m. - 7:30 a.m.
|
Machine Learning and Morphology: Opportunities and Challenges
(
Invited Talk
)
>
SlidesLive Video
|
Wilfried Wöber
🔗
|
Sat 7:30 a.m. - 8:00 a.m.
|
Dissociating Language and Thought in Large Language Models
(
Invited Talk
)
>
SlidesLive Video
|
Anna Ivanova
🔗
|
Sat 8:00 a.m. - 8:30 a.m.
|
Coffee Break
|
🔗
|
Sat 8:30 a.m. - 8:35 a.m.
|
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
(
Spotlight
)
>
link
SlidesLive Video
|
Leo Schwinn · David Dobre · Stephan Günnemann · Gauthier Gidel
🔗
|
Sat 8:35 a.m. - 8:40 a.m.
|
Compositional Generalization in Vision-Language Models uses the Language Modality only
(
Spotlight
)
>
link
SlidesLive Video
|
🔗
|
Sat 8:40 a.m. - 8:45 a.m.
|
A Study on the Calibration of In-context Learning
(
Spotlight
)
>
link
|
🔗
|
Sat 8:45 a.m. - 8:50 a.m.
|
Can LLM-Generated Misinformation Be Detected?
(
Spotlight
)
>
link
SlidesLive Video
|
Canyu Chen · Kai Shu
🔗
|
Sat 8:50 a.m. - 8:55 a.m.
|
Self-Evaluation Improves Selective Generation in Large Language Models
(
Spotlight
)
>
link
SlidesLive Video
|
Jie Ren · Yao Zhao · Tu Vu · Peter Liu · Balaji Lakshminarayanan
🔗
|
Sat 8:55 a.m. - 9:00 a.m.
|
Filter bubbles and affective polarization in user-personalized large language model outputs
(
Spotlight
)
>
link
SlidesLive Video
|
Tomo Lazovich
🔗
|
Sat 9:00 a.m. - 10:30 a.m.
|
Poster Session
(
Poster Session
)
>
|
🔗
|
Sat 10:30 a.m. - 12:00 p.m.
|
Lunch
(
Lunch Break
)
>
|
🔗
|
Sat 12:00 p.m. - 12:30 p.m.
|
Active and Online Learning with Large (and Combinatorial) Models
(
Invited Talk
)
>
SlidesLive Video
|
🔗
|
Sat 12:30 p.m. - 12:40 p.m.
|
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
(
Contributed talk
)
>
link
SlidesLive Video
|
🔗
|
Sat 12:40 p.m. - 12:50 p.m.
|
A Natural Experiment on LLM Data Contamination in Code Generation
(
Contributed talk
)
>
link
SlidesLive Video
|
🔗
|
Sat 12:50 p.m. - 1:00 p.m.
|
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
(
Contributed talk
)
>
link
SlidesLive Video
|
🔗
|
Sat 1:00 p.m. - 1:30 p.m.
|
Coffee Break
(
Coffee Break
)
>
|
🔗
|
Sat 1:30 p.m. - 2:00 p.m.
|
Limitations of Fine-Tuning for Aligning LLMs
(
Invited Talk
)
>
SlidesLive Video
|
David Krueger
🔗
|
Sat 2:00 p.m. - 2:30 p.m.
|
Measurement in the Age of LLMs: An Application to Political Ideology Scaling
(
Invited Talk
)
>
SlidesLive Video
|
Aaron Schein
🔗
|
Sat 2:30 p.m. - 3:20 p.m.
|
Panel: Failure Modes in the Age of Foundation Models. (David Krueger, Christoph Lampert, Tatiana Likhomanenko, Aaron Schein. Moderator: Naomi Saphra)
(
Panel Discussion
)
>
SlidesLive Video
|
🔗
|
Sat 3:20 p.m. - 3:30 p.m.
|
Closing Remarks (Awards and outlook)
(
Ending Comments
)
>
SlidesLive Video
|
Yubin Xie
🔗
|
-
|
Do Language Models Know When They're Hallucinating References?
(
Poster
)
>
link
|
Ayush Agrawal · Mirac Suzgun · Lester Mackey · Adam Tauman Kalai
🔗
|
-
|
From Failures to Factuality: A Study on ChatGPT in Open-Domain QA
(
Poster
)
>
link
|
Shen Zheng · Jie Huang · Kevin Chang
🔗
|
-
|
On the performance of Multimodal Language Models
(
Poster
)
>
link
|
Utsav Garg · Erhan Bas
🔗
|
-
|
Transformer-Based Large Language Models Are Not General Learners: A Universal Circuit Perspective
(
Poster
)
>
link
|
Yang Chen · Yitao Liang · Zhouchen Lin
🔗
|
-
|
A Study on Improving Reasoning in Language Models
(
Poster
)
>
link
|
Yuqing Du · Alexander Havrilla · Sainbayar Sukhbaatar · Pieter Abbeel · Roberta Raileanu
🔗
|
-
|
Interactive Model Correction with Natural Language
(
Poster
)
>
link
|
Yoonho Lee · Michelle Lam · Helena Vasconcelos · Michael Bernstein · Chelsea Finn
🔗
|
-
|
Structure-Aware Path Inference for Neural Finite State Transducers
(
Poster
)
>
link
|
Weiting Tan · Chu-Cheng Lin · Jason Eisner
🔗
|
-
|
Analyzing the factual knowledge of parameter efficient instruction tuned mid-size Large Language Models
(
Poster
)
>
link
|
Anmol Nayak · Hari prasad Timmapathini
🔗
|
-
|
Beyond Erdos-Renyi: Generalization in Algorithmic Reasoning on Graphs
(
Poster
)
>
link
|
Dobrik Georgiev · Pietro Lió · Jakub Bachurski · Junhua Chen · Tunan Shi
🔗
|
-
|
Exploring and Improving the Spatial Reasoning Abilities of Large Language Models
(
Poster
)
>
link
|
Manasi Sharma
🔗
|
-
|
Towards Better Understanding of Domain Shift on Linear-Probed Visual Foundation Models
(
Poster
)
>
link
|
Eric Heim
🔗
|
-
|
How Many Raters Do You Need? Power Analysis for Foundation Models
(
Poster
)
>
link
|
Christopher Homan · Shira Wein · Chris Welty · Lora Aroyo
🔗
|
-
|
Can Visual Scratchpads With Diagrammatic Abstractions Augment LLM Reasoning?
(
Poster
)
>
link
|
Joy Hsu · Gabriel Poesia · Jiajun Wu · Noah Goodman
🔗
|
-
|
Exploring DINO: Emergent Properties and Limitations for Synthetic Aperture Radar Imagery
(
Poster
)
>
link
|
Joseph Alejandro Gallego Mejia · Anna Jungbluth · Laura Martínez-Ferrer · Francisco Dorr · Matthew Allen · Freddie Kalaitzis · Raul Ramos-Pollán
🔗
|
-
|
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
(
Poster
)
>
link
|
Lukas Berglund · Meg Tong · Maximilian Kaufmann · Mikita Balesni · Asa Cooper Stickland · Tomasz Korbak · Owain Evans
🔗
|
-
|
Hallucination of Large Language Models in Finance: An Empirical Examination
(
Poster
)
>
link
|
Haoqiang Kang · Xiao-Yang Liu
🔗
|
-
|
Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months
(
Poster
)
>
link
|
Fady Rezk · Antreas Antoniou · Henry Gouk · Timothy Hospedales
🔗
|
-
|
Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation
(
Poster
)
>
link
|
Yuhui Zhang · Brandon McKinzie · Zhe Gan · Vaishaal Shankar · Alexander Toshev
🔗
|
-
|
SentimentPulse: Temporal-Aware Custom Language Models vs. GPT-3.5 for Consumer Sentiment
(
Poster
)
>
link
|
Lixiang Li · Nagender Aneja · Alina Nesen · Bharat Bhargava
🔗
|
-
|
Compositional Generalization in Vision-Language Models uses the Language Modality only
(
Poster
)
>
link
|
Chenwei Wu · Patrick Haffner · Erran Li Li · Stefano Ermon · Rong Ge
🔗
|
-
|
A Negative Result on Gradient Matching for Selective Backprop
(
Poster
)
>
link
|
Lukas Balles · Cedric Archambeau · Giovanni Zappella
🔗
|
-
|
Can Segment Anything Model Improve Semantic Segmentation?
(
Poster
)
>
link
|
Maryam Qamar · Chaoning Zhang · Donghoon Kim · Muhammad Salman Ali · Sung-Ho Bae
🔗
|
-
|
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
(
Poster
)
>
link
|
Aleksandar Petrov · Philip Torr · Adel Bibi
🔗
|
-
|
A Study on the Calibration of In-context Learning
(
Spotlight
)
>
|
Hanlin Zhang · yifan zhang · Yaodong Yu · Eric Xing · Himabindu Lakkaraju · Sham Kakade
🔗
|
-
|
Segment Anything Model (SAM) Enhances Pseudo-Labels for Weakly Supervised Semantic Segmentation
(
Poster
)
>
link
|
Tianle Chen · Zheda Mai · Ruiwen Li · Wei-Lun (Harry) Chao
🔗
|
-
|
An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics
(
Poster
)
>
link
|
Saba Ahmadi · Aishwarya Agrawal
🔗
|
-
|
Zero-shot capabilities of visual language models with prompt engineering for images of animals
(
Poster
)
>
link
|
Andrea Tejeda Ocampo · Eric C. Orenstein · Kakani Katija
🔗
|
-
|
Surprising Deviations from Bayesian View in In-Context Learning
(
Poster
)
>
link
|
Madhur Panwar · Kabir Ahuja · Navin Goyal
🔗
|
-
|
Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models
(
Poster
)
>
link
|
Adhithya Prakash Saravanan · Rafal Kocielnik · Roy Jiang · Pengrui Han · Animashree Anandkumar
🔗
|
-
|
How (not) to ensemble LVLMs for VQA
(
Poster
)
>
link
|
Lisa Alazraki · Lluis Castrejon · Mostafa Dehghani · Fantine Huot · Jasper Uijlings · Thomas Mensink
🔗
|
-
|
A Natural Experiment on LLM Data Contamination in Code Generation
(
Poster
)
>
link
|
Manley Roberts · Himanshu Thakur · Christine Herlihy · Colin White · Samuel Dooley
🔗
|
-
|
Are large language models good annotators?
(
Poster
)
>
link
|
Jay Mohta · Kenan Ak · Yan Xu · Mingwei Shen
🔗
|