Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
AI & ML interests
None defined yet.
Recent Activity
View all activity
Distilling Diverse Vision Foundation Models for Robot Learning
-
theaiinstitute/theia-tiny-patch16-224-cdiv
Feature Extraction • 10M • Updated • 448 • 4 -
theaiinstitute/theia-small-patch16-224-cdiv
Feature Extraction • 36.7M • Updated • 197 • 3 -
theaiinstitute/theia-base-patch16-224-cdiv
Feature Extraction • 0.1B • Updated • 1.52k • 9 -
theaiinstitute/theia-tiny-patch16-224-cddsv
Feature Extraction • 16.2M • Updated • 1.74k • 4
Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
Distilling Diverse Vision Foundation Models for Robot Learning
-
theaiinstitute/theia-tiny-patch16-224-cdiv
Feature Extraction • 10M • Updated • 448 • 4 -
theaiinstitute/theia-small-patch16-224-cdiv
Feature Extraction • 36.7M • Updated • 197 • 3 -
theaiinstitute/theia-base-patch16-224-cdiv
Feature Extraction • 0.1B • Updated • 1.52k • 9 -
theaiinstitute/theia-tiny-patch16-224-cddsv
Feature Extraction • 16.2M • Updated • 1.74k • 4