Rui Liu

lr10260's activity

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

updated a model 4 days ago

lr10260/DUPL-3B

4B • Updated 4 days ago • 15

published a model 4 days ago

lr10260/DUPL-3B

4B • Updated 4 days ago • 15

updated a dataset 10 days ago

lr10260/rlaif_v_filtered

Viewer • Updated 10 days ago • 82.9k • 37

published a dataset 10 days ago

lr10260/rlaif_v_filtered

Viewer • Updated 10 days ago • 82.9k • 37

upvoted a paper 11 days ago

Reinforcing Multimodal Reasoning Against Visual Degradation

Paper • 2605.09262 • Published 15 days ago • 7

updated a model 11 days ago

lr10260/DUPL-4B

5B • Updated 11 days ago • 16

published a model 11 days ago

lr10260/DUPL-4B

5B • Updated 11 days ago • 16

updated a model 11 days ago

lr10260/DUPL-8B

9B • Updated 11 days ago • 12

published 2 models 11 days ago

lr10260/DUPL-8B

9B • Updated 11 days ago • 12

lr10260/qwen3-vl-8b-mmrl-grpo-step100

9B • Updated Apr 10 • 10

authored a paper 13 days ago

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

Paper • 2605.09269 • Published 15 days ago • 6

submitted a paper to Daily Papers 13 days ago

Reinforcing Multimodal Reasoning Against Visual Degradation

Paper • 2605.09262 • Published 15 days ago • 7

upvoted a paper 13 days ago

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

Paper • 2605.09269 • Published 15 days ago • 6

submitted a paper to Daily Papers 13 days ago

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

Paper • 2605.09269 • Published 15 days ago • 6

New activity in lr10260/rm-sder 14 days ago

[bot] Conversion to Parquet

#1 opened 2 months ago by

parquet-converter

updated a model 14 days ago

lr10260/GRPO-8B

9B • Updated 14 days ago • 24

published a model 14 days ago

lr10260/GRPO-8B

9B • Updated 14 days ago • 24

updated a model 14 days ago

lr10260/GRPO-4B

5B • Updated 14 days ago • 26

published a model 14 days ago

lr10260/GRPO-4B

5B • Updated 14 days ago • 26

updated a model 14 days ago

lr10260/DUPL-D-7B

8B • Updated 14 days ago • 15