theaiinstitute/sole-r1-sft
Updated
SOLE-R1
Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
-
-
theaiinstitute/sole-r1-sft-grpo
Updated -
theaiinstitute/sole-r1-sft-no-nonexpert
Updated -
theaiinstitute/sole-r1-sft-no-oxe
Updated -
theaiinstitute/sole-r1-sft-no-think
Updated -
theaiinstitute/sole-r1-main-dataset
Preview • Updated • 376 -
theaiinstitute/sole-r1-oxe-annot-1026
Viewer • Updated • 653k • 561 -
theaiinstitute/sole-r1-robocasa-annot-0717
Preview • Updated • 535