Ping Yu

RESTRAIN: From Spurious Votes to Signals — Self-Training RL with Self-Penalization

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning

Hybrid Reinforcement: when reward is sparse, better to be dense

Jointly Reinforcing Diversity and Quality in Language Model Generations

Adaptive Decoding via Latent Preference Optimization

Bridging Offline and Online Reinforcement Learning for LLMs

Diverse Preference Optimization

CoT-Self-Instruct: Building high-quality synthetic prompts data for reasoning and non-reasoning tasks

Self-Taught Evaluators

R.I.P.: Better Models by Survival of the Fittest Prompts