Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
Paper
•
2512.13080
•
Published
•
15
BeingBeyond
BeingBeyond-wpz
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
13 days ago
Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
upvoted
a
paper
26 days ago
DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models
Organizations
None yet
upvoted
a
paper
13 days ago