IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance
Paper
•
2601.16207
•
Published
•
6
Cristina Mata
cfmata
AI & ML interests
None yet
Recent Activity
authored
a paper
about 19 hours ago
IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance
upvoted
a
paper
9 days ago
Future Optical Flow Prediction Improves Robot Control & Video Generation
upvoted
a
paper
over 1 year ago
Theia: Distilling Diverse Vision Foundation Models for Robot Learning
Organizations
None yet
authored
a
paper
about 19 hours ago
authored
a
paper
over 1 year ago