影响力指数

-/100

发表论文2 篇

平均评分4.3

年均产出2.0 篇/年

Di Wu

MS student@Tongji University·中国·OpenReview

EAPO: Expert-guided Adaptive Preference Optimization for Recommendation

ICLR 2026Rejected

On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning

ICLR 2026Withdrawn

合作者 (12)