Thomas Weng

thomasweng's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection about 1 month ago

SOLE-R1

Collection

Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning • 8 items • Updated May 12

published 3 datasets about 1 month ago

theaiinstitute/sole-r1-robocasa-annot-0717

Preview • Updated May 11 • 2.23k

theaiinstitute/sole-r1-oxe-annot-1026

Preview • Updated May 11 • 653k • 1.66k

theaiinstitute/sole-r1-main-dataset

Preview • Updated May 11 • 5.14k

published 5 models about 1 month ago

theaiinstitute/sole-r1-sft-no-think

Updated May 11

theaiinstitute/sole-r1-sft-no-oxe

Updated May 11

theaiinstitute/sole-r1-sft-no-nonexpert

Updated May 11

theaiinstitute/sole-r1-sft-grpo

Updated May 11

theaiinstitute/sole-r1-sft

Updated May 11

updated 3 datasets about 1 month ago

theaiinstitute/sole-r1-robocasa-annot-0717

Preview • Updated May 11 • 2.23k

theaiinstitute/sole-r1-oxe-annot-1026

Preview • Updated May 11 • 653k • 1.66k

theaiinstitute/sole-r1-main-dataset

Preview • Updated May 11 • 5.14k

updated a collection about 1 month ago

SOLE-R1

Collection

Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning • 8 items • Updated May 12

updated a model about 1 month ago

theaiinstitute/sole-r1-sft-no-oxe

Updated May 11