PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding

Journal:
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Published:
DOI:
10.1109/iros60139.2025.11247519
Affiliations:
5
Authors:
12
Go to article
Institutions Authors Share
Hong Kong University of Science and Technology (Guangzhou), China
5.500000
 0.46
Westlake University, China
3.000000
 0.25
Harbin Institute of Technology (HIT), China
1.500000
 0.13
Zhejiang University (ZJU), China
1.000000
 0.08
Monash University, Australia
1.000000
 0.08
Interested in Machine Learning?