arxiv:2602.08321
Xiao Liu
lx865712528
AI & ML interests
NLP, LLM and reasoning
Recent Activity
authored
a paper
6 days ago
Improving Data and Reward Design for Scientific Reasoning in Large Language Models
upvoted
a
paper
6 days ago
Improving Data and Reward Design for Scientific Reasoning in Large Language Models
authored
a paper
8 days ago
MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration
Organizations
