Papers
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering
Zhuowei Li, Haizhou Shi, Yunhe Gao et al.
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
Zihao Wang, Yibo Jiang, Jiahao Yu et al.
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
Walter Mayor, Johan Obando-Ceron, Aaron Courville et al.
The impact of uncertainty on regularized learning in games
Pierre-Louis Cauvin, Davide Legacci, Panayotis Mertikopoulos
The Importance of Being Lazy: Scaling Limits of Continual Learning
Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta et al.
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
Kristina Nikolić, Luze Sun, Jie Zhang et al.
The Limits of Predicting Agents from Behaviour
Alexis Bellot, Jonathan Richens, Tom Everitt
The Limits of Tractable Marginalization
Oliver Broadrick, Sanyam Agarwal, Guy Van Den Broeck et al.
The Lock-in Hypothesis: Stagnation by Algorithm
Tianyi Qiu, Zhonghao He, Tejasveer Chugh et al.
The Missing Alignment Link of In-context Learning on Sequences
Harshvardhan Agarwal, Sunita Sarawagi
The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction
Alex Kokot, Octavian-Vlad Murad, Marina Meila
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
Pedro Pinto Santos, Alberto Sardinha, Francisco S. Melo
Theoretical guarantees on the best-of-n alignment policy
Ahmad Beirami, Alekh Agarwal, Jonathan Berant et al.
Theoretical Limitations of Ensembles in the Age of Overparameterization
Niclas Dern, John Patrick Cunningham, Geoff Pleiss
Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
Quan Minh Nguyen, Minh N. Vu, Truc Nguyen et al.
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
Jayadev Naram, Fredrik Hellström, Ziming Wang et al.
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
Shiwei Li, Xiandi Luo, Haozhao Wang et al.
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
Lukas Fluri, Leon Lang, Alessandro Abate et al.
The Polynomial Stein Discrepancy for Assessing Moment Convergence
Narayan Srinivasan, Matthew Sutton, Christopher Drovandi et al.
The Power of Random Features and the Limits of Distribution-Free Gradient Descent
Ari Karchmer, Eran Malach
The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
Yuqing Xie, Ameya Daigavane, Mit Kotak et al.
The Price of Linear Time: Error Analysis of Structured Kernel Interpolation
Alexander Moreno, Justin Xiao, Jonathan Mei
The Relationship Between No-Regret Learning and Online Conformal Prediction
Ramya Ramalingam, Shayan Kiyani, Aaron Roth