Vincent Zhuang

Reliable Fine-Grained Evaluation of Natural Language Math Proofs

See it to Place it: Evolving Macro Placements with Vision Language Models

Training Language Models to Self-Correct via Reinforcement Learning

Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models