影响力指数

28.4/100

前 26.3%

全站排名 #16,942

发表论文5 篇

平均评分5.2

年均产出1.7 篇/年

Bo Xue

PhD student@City University of Hong Kong·中国香港·OpenReview

研究方向

online learing · bandits · stochatic optimization

Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning

ICLR 2026Desk Rejected

Multi-Objective Bandits with Hierarchical Preferences: A Thompson Sampling Approach

ICLR 2026Withdrawn

TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

NeurIPS 2025Poster

Multi-objective Linear Reinforcement Learning with Lexicographic Rewards

ICML 2025Poster

合作者 (18)

博士导师5 篇