Runpeng Dai

Leo-Dai's activity

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

authored 3 papers 8 days ago

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

Paper • 2605.09269 • Published 11 days ago • 6

Reinforcing Multimodal Reasoning Against Visual Degradation

Paper • 2605.09262 • Published 11 days ago • 7

G-Zero: Self-Play for Open-Ended Generation from Zero Data

Paper • 2605.09959 • Published 10 days ago • 17

upvoted 3 papers 9 days ago

G-Zero: Self-Play for Open-Ended Generation from Zero Data

Paper • 2605.09959 • Published 10 days ago • 17

Reinforcing Multimodal Reasoning Against Visual Degradation

Paper • 2605.09262 • Published 11 days ago • 7

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

Paper • 2605.09269 • Published 11 days ago • 6

authored a paper 9 days ago

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Paper • 2605.08083 • Published 13 days ago • 66

upvoted a paper 10 days ago

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Paper • 2605.08083 • Published 13 days ago • 66

upvoted a paper 2 months ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published Mar 17 • 139

updated 3 datasets 3 months ago

Leo-Dai/APO_AIME24

Viewer • Updated Mar 2 • 30 • 9

Leo-Dai/APO_AIME25

Viewer • Updated Mar 2 • 30 • 11

Leo-Dai/APO_AMC23

Viewer • Updated Mar 2 • 40 • 8

liked a Space 3 months ago

Running

3

Efficient Reasoning Online Judgement

📉

3

upvoted a paper 3 months ago

Training Data Efficiency in Multimodal Process Reward Models

Paper • 2602.04145 • Published Feb 4 • 79

authored a paper 4 months ago

Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

Paper • 2602.03845 • Published Feb 3 • 27

upvoted 3 papers 4 months ago

Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation

Paper • 2602.03619 • Published Feb 3 • 28

Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

Paper • 2602.03845 • Published Feb 3 • 27

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published Jan 8 • 31

upvoted a paper 5 months ago

MotionEdit: Benchmarking and Learning Motion-Centric Image Editing

Paper • 2512.10284 • Published Dec 11, 2025 • 26

upvoted a paper 6 months ago

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

Paper • 2511.21662 • Published Nov 26, 2025 • 11