Ben Zhou

CORE: Concept-Oriented Reinforcement for Bridging the Definition–Application Gap in Mathematical Reasoning

BOW: Reinforcement Learning for Bottlenecked Next-word Prediction

CC-Learn: Cohort-Based Consistency Learning

ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation

Unbiased Visual Reasoning with Controlled Visual Inputs

BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation