Preprint Accelerating Diffusion Models in Offline RL via Reward-Aware Consistency Trajectory Distillation 2025 Duan X, He Y, Tajwar F, Salakhutdinov R, Kolter JZ, Schneider J
Preprint Adversarial Attacks on Robotic Vision Language Action Models 2025 Jones EK, Robey A, Zou A, Ravichandran Z, Pappas GJ, Hassani H, Fredrikson M, Kolter JZ
Preprint Antidistillation Sampling 2025 Savani Y, Trockman A, Feng Z, Xu YE, Schwarzschild A, Robey A, Finzi M, Kolter JZ
Preprint Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation 2025 He Y, Robey A, Murata N, Jiang Y, Williams JN, Pappas GJ, Hassani H, Mitsufuji Y, Salakhutdinov R, Kolter JZ
Preprint Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion 2025 Dontas M, He Y, Murata N, Mitsufuji Y, Kolter JZ, Salakhutdinov R
Preprint Compute-Optimal LLMs Provably Generalize Better With Scale 2025 Finzi M, Kapoor S, Granziol D, Gu A, De Sa C, Kolter JZ, Wilson AG
Preprint D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models 2025 Krishna S, Zou A, Gupta R, Jones EK, Winter N, Hendrycks D, Kolter JZ, Fredrikson M, Matsoukas S
Preprint Dojo: A Differentiable Physics Engine for Robotics 2025 Howell TA, Cleac'h SL, Brüdigam J, Chen Q, Sun J, Kolter JZ, Schwager M, Manchester Z
Preprint Evaluating Language Model Reasoning about Confidential Information 2025 Sam D, Robey A, Zou A, Fredrikson M, Kolter JZ
Preprint Existing Large Language Model Unlearning Evaluations Are Inconclusive 2025 Feng Z, Xu YE, Robey A, Kirk R, Davies X, Gal Y, Schwarzschild A, Kolter JZ
Preprint Finetuning CLIP to Reason about Pairwise Differences 2025 Sam D, Willmott D, Semedo JD, Kolter JZ
Preprint Improved Mean Flows: On the Challenges of Fastforward Generative Models 2025 Geng Z, Lu Y, Wu Z, Shechtman E, Kolter JZ, He K
Preprint Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models 2025 Ai X, He Y, Gu A, Salakhutdinov R, Kolter JZ, Boffi NM, Simchowitz M
Journal Article Large Scale Bilevel Optimization for N-K SCOPF Using Adversarial Robustness 2025 • IEEE Transactions on Power Systems • 40(6):5209-5220 Agarwal A, Donti PL, Kolter JZ, Pileggi L
Preprint Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning 2025 Xu YE, Savani Y, Fang F, Kolter JZ
Preprint OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics 2025 Dorna V, Mekala A, Zhao W, McCallum A, Lipton ZC, Kolter JZ, Maini P
Preprint Predicting the Performance of Black-box LLMs through Follow-up Queries 2025 Sam D, Finzi M, Kolter JZ
Preprint Reevaluating Policy Gradient Methods for Imperfect-Information Games 2025 Rudolph M, Lichtle N, Mohammadpour S, Bayen A, Kolter JZ, Zhang A, Farina G, Vinitsky E, Sokota S
Preprint Safety Pretraining: Toward the Next Generation of Safe AI 2025 Maini P, Goyal S, Sam D, Robey A, Savani Y, Jiang Y, Zou A, Fredrikson M, Lipton ZC, Kolter JZ
Preprint Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition 2025 Zou A, Lin M, Jones E, Nowak M, Dziemian M, Winter N, Grattan A, Nathanael V, Croft A, Davies X, Patel J, Kirk R, Burnikell N, Gal Y, Hendrycks D, Kolter JZ, Fredrikson M
Preprint Superhuman AI for Stratego Using Self-Play Reinforcement Learning and Test-Time Search 2025 Sokota S, Vinitsky E, Hu H, Kolter JZ, Farina G
Preprint Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners 2025 Paliotta D, Wang J, Pagliardini M, Li KY, Bick A, Kolter JZ, Gu A, Fleuret F, Dao T
