Minghui Dong

1. MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation
   2025/03/26 by Rongyu Zhang, Minghui Dong, Zhang, Rongyu +15 · 16 citations
   Computer Science · Engineering · #Multimodal Machine Learning Applications #Robot Manipulation and Learning #Natural Language Processing Techniques