CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
Paper
•
2508.21046
•
Published
•
9
liwei
liwei2013
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
CogVLA: Cognition-Aligned Vision-Language-Action Model via
Instruction-Driven Routing & Sparsification
authored
a paper
about 1 month ago
LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant
Organizations
None yet
upvoted
a
paper
about 1 month ago