Shaobo Wang

PhD student, Shanghai Jiaotong University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

#3714 · Zichen Wen, Shaobo Wang, Yufa Zhou, Junyuan Zhang, Qintong Zhang, Yifeng Gao, Zhaorun Chen, Bin Wang, Weijia Li, Conghui He, Linfeng Zhang

We propose a progressive consistency distillation framework that enhances the efficiency of MLLMs by significantly reducing computational cost while preserving strong performance.