UGPhysics

AI & ML interests

None defined yet.

Recent Activity

dandingsky  authored a paper 1 day ago

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

dandingsky  authored a paper 1 day ago

Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models

dandingsky  authored a paper 1 day ago

Progressive Residual Warmup for Language Model Pretraining

View all activity

Team members 4