Xu's picture

4

Xu

kaishxu

·

AI & ML interests

None yet

Recent Activity

authored a paper about 2 months ago

Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework

upvoted a paper about 2 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

updated a model about 2 months ago

kaishxu/RISE-Qwen2-7B

View all activity

Organizations

None yet

Papers 8

arxiv:2502.18874

arxiv:2410.06638

arxiv:2410.01556

arxiv:2402.12844

models 2

kaishxu/RISE-Qwen2-7B

8B • Updated Jun 2 • 2 • 1

kaishxu/ARJudge

8B • Updated Jun 2 • 2

datasets 0

None public yet