影响力指数

42.64/100

前 12.6%

全站排名 #8,101

发表论文5 篇

平均评分5.0

年均产出1.7 篇/年

Wendi Li

PhD student@University of Wisconsin - Madison·美国·OpenReview

General Exploratory Bonus for Optimistic Exploration in RLHF

ICLR 2026Poster

Process Reinforcement through Implicit Rewards

ICLR 2026Rejected

Process Reward Model with Q-value Rankings

ICLR 2025Poster

Free Process Rewards without Process Labels

ICML 2025Poster

合作者 (20)