影响力指数

66.24/100

前 3.3%

全站排名 #2,155

发表论文9 篇

平均评分6.3

年均产出3.0 篇/年

Liyuan Mao

PhD student@Shanghai Jiaotong University·中国·OpenReview

研究方向

Reinforcement Learning from Human Feedback · Reinforcement Learning

Dichotomous Diffusion Policy Optimization

ICLR 2026Poster

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning

ICLR 2026Withdrawn

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

Information-Theoretic Reward Decomposition for Generalizable RLHF

NeurIPS 2025Poster

Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization

NeurIPS 2025Poster

合作者 (20)