lr10260/GRPO-8B
9B • Updated
Rui Liu
lr10260
·
AI & ML interests
None yet
Recent Activity
authored a paper about 15 hours ago
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification upvoted a paper about 20 hours ago
Reinforcing Multimodal Reasoning Against Visual Degradation submitted a paper about 20 hours ago
Reinforcing Multimodal Reasoning Against Visual DegradationOrganizations
lr10260/GRPO-4B
5B • Updated
lr10260/ROMA-4B
5B • Updated
lr10260/ROMA-8B
9B • Updated
lr10260/DUPL-D-7B
8B • Updated
lr10260/DUPL-G-7B
8B • Updated
lr10260/StaticRubric-8B
9B • Updated
lr10260/NoRubric-8B
9B • Updated
lr10260/DeltaRubric-8B
9B • Updated
lr10260/DeltaRubric-4B
5B • Updated
lr10260/DeltaRubric-Curriculum-8B
9B • Updated
lr10260/DeltaRubric-Text-Only-Planner-8B
9B • Updated
lr10260/DeltaRubric
Updated
lr10260/3b-grpo-n5
4B • Updated • 1
lr10260/3b-vogue
4B • Updated • 1
lr10260/7b-grpo-n8
8B • Updated • 1
lr10260/7b-vogue-n8
8B • Updated • 1
lr10260/7b-grpo-vision-120
8B • Updated • 1
lr10260/3b-grpo-vision-120
4B • Updated • 1
lr10260/3b-mssr-vision-120
4B • Updated • 1
lr10260/7b-mssr-vision-120
8B • Updated • 1