影响力指数

-/100

发表论文1 篇

平均评分3.5

年均产出1.0 篇/年

Jiaxin Fan

Undergrad student@tongji university·中国·OpenReview

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

ICLR 2026Withdrawn

合作者 (6)