NeurIPS 2024 Conference Submissions

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Declan Iain Campbell, Sunayana Rane, Tyler Giallanza, C. Nicolò De Sabbata, Kia Ghods, Amogh Joshi, Alexander Ku, Steven M Frankland, Thomas L. Griffiths, Jonathan D. Cohen, Taylor Whittington Webb
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Reward Machines for Deep RL in Noisy and Uncertain Environments
Andrew C Li, Zizhao Chen, Toryn Q. Klassen, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila A. McIlraith
- Published: 25 Sept 2024, Last Modified: 15 Jan 2025
- NeurIPS 2024 poster
- Readers: Everyone
Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
Yue Yu, Ning Liu, Fei Lu, Tian Gao, Siavash Jafarzadeh, Stewart A Silling
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 spotlight
- Readers: Everyone
Sample Efficient Bayesian Learning of Causal Graphs from Interventions
Zihan Zhou, Muhammad Qasim Elahi, Murat Kocaoglu
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
Core Francisco Park, Maya Okawa, Andrew Lee, Ekdeep Singh Lubana, Hidenori Tanaka
- Published: 25 Sept 2024, Last Modified: 18 Dec 2024
- NeurIPS 2024 spotlight
- Readers: Everyone
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Ruiquan Huang, Yingbin Liang, Jing Yang
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Active, anytime-valid risk controlling prediction sets
Ziyu Xu, Nikos Karampatziakis, Paul Mineiro
- Published: 25 Sept 2024, Last Modified: 15 Jan 2025
- NeurIPS 2024 poster
- Readers: Everyone
Continual learning with the neural tangent ensemble
Ari S Benjamin, Christian-Gernot Pehle, Kyle Daruwalla
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 spotlight
- Readers: Everyone
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip Torr, Amartya Sanyal, Puneet K. Dokania
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Neglected Hessian component explains mysteries in sharpness regularization
Yann Dauphin, Atish Agarwala, Hossein Mobahi
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 spotlight
- Readers: Everyone
Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
Christian Schmid, James M Murray
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Semantics and Spatiality of Emergent Communication
Rotem Ben Zion, Boaz Carmeli, Orr Paradise, Yonatan Belinkov
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
Ipsita Ghosh, Abiy Tasissa, Christian Kümmerle
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
Gavia Gray, Aman Tiwari, Shane Bergsma, Joel Hestness
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
An Analysis of Tokenization: Transformers under Markov Data
Nived Rajaraman, Jiantao Jiao, Kannan Ramchandran
- Published: 25 Sept 2024, Last Modified: 15 Nov 2024
- NeurIPS 2024 spotlight
- Readers: Everyone
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
William Brandon, Mayank Mishra, Aniruddha Nrusimha, Rameswar Panda, Jonathan Ragan-Kelley
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Symmetry Discovery Beyond Affine Transformations
Ben Shaw, Abram Magner, Kevin R. Moon
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
On the Inductive Bias of Stacking Towards Improving Reasoning
Nikunj Saunshi, Stefani Karp, Shankar Krishnan, Sobhan Miryoosefi, Sashank J. Reddi, Sanjiv Kumar
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
Pasan Dissanayake, Sanghamitra Dutta
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
Samuel Lippl, Jack Lindsey
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Communication Efficient Distributed Training with Distributed Lion
Bo Liu, Lemeng Wu, Lizhang Chen, Kaizhao Liang, Jiaxu Zhu, Chen Liang, Raghuraman Krishnamoorthi, qiang liu
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Aligning LLM Agents by Learning Latent Preference from User Edits
Ge Gao, Alexey Taymanov, Eduardo Salinas, Paul Mineiro, Dipendra Misra
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Can Models Learn Skill Composition from Examples?
Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, Sanjeev Arora
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Learning from Snapshots of Discrete and Continuous Data Streams
Pramith Devulapalli, Steve Hanneke
- Published: 25 Sept 2024, Last Modified: 06 Nov 2024
- NeurIPS 2024 poster
- Readers: Everyone
Generalization Analysis for Label-Specific Representation Learning
Yifan Zhang, Min-Ling Zhang
- Published: 25 Sept 2024, Last Modified: 30 Dec 2024
- NeurIPS 2024 spotlight
- Readers: Everyone