Ke Li's picture

1 3

Ke Li

tristanli

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

LTD-Bench: Evaluating Large Language Models by Letting Them Draw

commented on a paper about 1 month ago

LTD-Bench: Evaluating Large Language Models by Letting Them Draw

upvoted a paper 2 months ago

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

View all activity

Organizations

None yet

upvoted a paper about 1 month ago

LTD-Bench: Evaluating Large Language Models by Letting Them Draw

Paper • 2511.02347 • Published Nov 4 • 8

upvoted 2 papers 2 months ago

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

Paper • 2509.22601 • Published Sep 26 • 29

Training-Free Group Relative Policy Optimization

Paper • 2510.08191 • Published Oct 9 • 44