Weizhe Yuan

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

StepWiser: Stepwise Generative Judges for Wiser Reasoning

Bridging Offline and Online Reinforcement Learning for LLMs

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

Self-Consistency Preference Optimization

FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios

Thinking LLMs: General Instruction Following with Thought Generation

Self-Taught Evaluators

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

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