Tianlu Wang

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

Bridging Offline and Online Reinforcement Learning for LLMs

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

ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context

Multi-Token Attention

Contextual Position Encoding: Learning to Count What’s Important

Self-Taught Evaluators

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge

Calibrate to Discriminate:Improve In-Context Learning with Label-Free Comparative Inference