影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
15.26/100
超过 46.4%
全站排名 #34,478
发表论文4 篇
平均评分
年均产出4.0 篇/年
Yuzi Yan
研究方向
Large Language Model · Multi-agent Reinforcement Learning
27
3D-Properties: Identifying Challenges in DPO and Charting a Path Forward
ICLR 2025Poster
一作17
Reward-Robust RLHF in LLMs
ICLR 2025Rejected
一作4
Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown
ICLR 2025Withdrawn
6
Boosting Deductive Reasoning with Step Signals In RLHF
ICLR 2025Rejected