Xiaojin Zhu

7

Papers

2

Total Citations

Papers (7)

Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?

NeurIPS 2025arXiv

Optimal Attack and Defense for Reinforcement Learning

Data Poisoning to Fake a Nash Equilibria for Markov Games

Provable Defense against Backdoor Policies in Reinforcement Learning

NeurIPS 2022arXiv

Mechanism Design for Collaborative Normal Mean Estimation

NeurIPS 2023arXiv

Dream the Impossible: Outlier Imagination with Diffusion Models

NeurIPS 2023arXiv