影响力指数

43.82/100

前 11.7%

全站排名 #7,560

发表论文8 篇

平均评分5.3

年均产出2.7 篇/年

Zizhan Zheng

Associate Professor@Tulane University·美国·OpenReview

研究方向

reinforcement learning · AI security · AI safety · generative AI

Robust Optimization for Mitigating Reward Hacking with Correlated Proxies

ICLR 2026Poster

Stealthy World Model Manipulation via Data Poisoning

ICLR 2026Rejected

Diffusion Guided Adversarial State Perturbations in Reinforcement Learning

NeurIPS 2025Poster

Robust Optimization for Mitigating Reward Hacking with Correlated Proxies

NeurIPS 2025Rejected

Diffusion Guided Adversarial State Perturbations in Reinforcement Learning

ICLR 2025Rejected

合作者 (10)

PhD Advisee6 篇

PhD Advisee2 篇

PhD Advisee2 篇