policy
DYSL_VLA
PKU-SEC-Lab · PyTorch
or hover any field below to flag it
Overview
Name
DYSL_VLA
Author
PKU-SEC-Lab
Framework
PyTorch
License
unknown
Skill type
manipulation
Evidence level
untested
Task description
Dysl-vla：Official code for "DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation". A framework that dynamically skips VLA layers based on action importance, achieving 3.75× speedup and 85.7× training reduction on robotic manipulation tas
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
0No robots list DYSL_VLA as compatible yet. Know of one? Flag it above.
Compatible environments
0No environments list DYSL_VLA yet.
Datasets that reference this policy
0No datasets reference DYSL_VLA yet.