Rui Lu's picture

1 3

Rui Lu

RayLuTHU

AI & ML interests

None yet

Recent Activity

upvoted a paper 4 days ago

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

authored a paper about 2 months ago

Augmenting Unsupervised Reinforcement Learning with Self-Reference

authored a paper about 2 months ago

Provable General Function Class Representation Learning in Multitask Bandits and MDPs

View all activity

Organizations

None yet

RayLuTHU's activity

upvoted a paper 4 days ago

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

Paper • 2506.01939 • Published 5 days ago • 129

upvoted a paper about 2 months ago

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published Apr 18 • 127

upvoted a paper 11 months ago

Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing

Paper • 2407.08770 • Published Jul 11, 2024 • 21