xuxin's picture

On Vacation 🏝️

3 9

xuxin

xx18

·

https://xinxu-ustc.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

upvoted a paper 30 days ago

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

upvoted a paper about 1 month ago

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

View all activity

Organizations

commented 2 papers 3 months ago

On Predictability of Reinforcement Learning Dynamics for Large Language Models

Paper • 2510.00553 • Published Oct 1, 2025 • 8 •

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

Paper • 2509.26226 • Published Sep 30, 2025 • 33 •

New activity in UGMathBench/ugmathbench 10 months ago

Update link to paper, add Github repo

#2 opened 10 months ago by