Kehan Chen

kehanchen

3

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

TACO: Tool-Augmented Credit Optimization for Agentic Tool Use

upvoted a paper 5 months ago

Improving Data and Reward Design for Scientific Reasoning in Large Language Models

upvoted a paper 5 months ago

MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration

View all activity

Organizations

None yet

upvoted a paper 1 day ago

TACO: Tool-Augmented Credit Optimization for Agentic Tool Use

Paper • 2606.30251 • Published 3 days ago • 15

upvoted 2 papers 5 months ago

Improving Data and Reward Design for Scientific Reasoning in Large Language Models

Paper • 2602.08321 • Published Feb 9 • 44

MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration

Paper • 2602.01734 • Published Feb 2 • 33