Yufei Wang

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation

AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent

Teaching LLMs According to Their Aptitude: Adaptive Switching Between CoT and TIR for Mathematical Problem Solving

SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model