MMODELYST
People/Chongyang Tao
PPL

Chongyang Tao

Papers (3)
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-InstructD$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement LearningUnsat Core Prediction through Polarity-Aware Representation Learning over Clause-Literal Hypergraphs