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
39.57/100
前 14.7%
全站排名 #9,471
发表论文7 篇
平均评分
年均产出2.3 篇/年
Olivier Delalleau
研究方向
large language models · deep reinforcement learning · deep neural networks · semi-supervised learning · manifold learning
20
Adversarial Training of Reward Models
COLM 2025Poster
28
HelpSteer2-Preference: Complementing Ratings with Preferences
ICLR 2025Poster
三作23
Diverging Preferences: When do Annotators Disagree and do Models Know?
ICLR 2025Rejected
10
Diverging Preferences: When do Annotators Disagree and do Models Know?
ICML 2025Poster