Xiaoyin Chen

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training

Latent Veracity Inference for Identifying Errors in Stepwise Reasoning

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Bayesian Symbolic Regression with Entropic Reinforcement Learning

Self-Evolving Curriculum for LLM Reasoning

PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation

Structure Language Models for Protein Conformation Generation

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Aligning Protein Conformation Ensemble Generation with Physical Feedback