LeonOverload

LeonOverload's activity

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

New activity in LeonOverload/primo-rl-json 1 day ago

[bot] Conversion to Parquet

#1 opened 2 days ago by

parquet-converter

upvoted a paper 2 days ago

V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators

Paper • 2604.03307 • Published 11 days ago • 14

updated 2 models 2 days ago

LeonOverload/PRIMO-COT-SFT-7B

Video-Text-to-Text • Updated 2 days ago

LeonOverload/PRIMO-R1-7B

Video-Text-to-Text • Updated 2 days ago

updated a collection 3 days ago

PRIMO R1

Collection

Official release of PRIMO R1, a 7B video MLLM for robotic process reasoning featuring RL-optimized models, SFT/RL datasets, and cross-domain benchmark • 6 items • Updated 3 days ago • 4

updated a dataset 3 days ago

LeonOverload/primo-bench-json

Viewer • Updated 2 days ago • 23.7k • 43

published a dataset 3 days ago

LeonOverload/primo-bench-json

Viewer • Updated 2 days ago • 23.7k • 43

updated a dataset 3 days ago

LeonOverload/primo-rl-json

Viewer • Updated 2 days ago • 328k • 43

published a dataset 3 days ago

LeonOverload/primo-rl-json

Viewer • Updated 2 days ago • 328k • 43

updated a dataset 3 days ago

LeonOverload/primo-sft-json

Viewer • Updated 2 days ago • 117k • 42

published a dataset 3 days ago

LeonOverload/primo-sft-json

Viewer • Updated 2 days ago • 117k • 42

New activity in LeonOverload/PRIMO-R1-7B 23 days ago

Update model card with description and paper link

#1 opened 23 days ago by

nielsr

New activity in LeonOverload/PRIMO-COT-SFT-7B 23 days ago

Improve model card and add paper link

#1 opened 23 days ago by

nielsr

commented a paper 24 days ago

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

Paper • 2603.15600 • Published 25 days ago • 7 •

3

updated a collection 24 days ago

PRIMO R1

Collection

Official release of PRIMO R1, a 7B video MLLM for robotic process reasoning featuring RL-optimized models, SFT/RL datasets, and cross-domain benchmark • 6 items • Updated 3 days ago • 4

upvoted a paper 24 days ago

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

Paper • 2603.15600 • Published 25 days ago • 7

upvoted a collection 24 days ago

PRIMO R1

Collection

Official release of PRIMO R1, a 7B video MLLM for robotic process reasoning featuring RL-optimized models, SFT/RL datasets, and cross-domain benchmark • 6 items • Updated 3 days ago • 4

updated a collection 25 days ago

PRIMO R1

Collection

Official release of PRIMO R1, a 7B video MLLM for robotic process reasoning featuring RL-optimized models, SFT/RL datasets, and cross-domain benchmark • 6 items • Updated 3 days ago • 4