PhD student, Shanghai Jiaotong University
4 papers at NeurIPS 2025
We propose a new paradigm to accelerate different components of the VLA model and achieved state-of-the-art performance.
A novel benchmark using a comprehensive preference dataset to evaluate multimodal judges across multiple key perspectives
We propose a progressive consistency distillation framework that enhances the efficiency of MLLMs by significantly reducing computational cost while preserving strong performance.
