Chengsong Huang

ChengsongHuang's activity

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

authored a paper 1 day ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 2 days ago • 39

upvoted a paper 1 day ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 2 days ago • 39

upvoted a paper 8 days ago

Surgical Post-Training: Cutting Errors, Keeping Knowledge

Paper • 2603.01683 • Published 10 days ago • 11

upvoted a paper 16 days ago

SkillOrchestra: Learning to Route Agents via Skill Transfer

Paper • 2602.19672 • Published 17 days ago • 55

upvoted a paper 22 days ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published 23 days ago • 107

upvoted a paper 23 days ago

Experiential Reinforcement Learning

Paper • 2602.13949 • Published 26 days ago • 70

upvoted a paper 29 days ago

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Paper • 2602.08234 • Published Feb 9 • 69

upvoted 3 papers about 1 month ago

EgoAVU: Egocentric Audio-Visual Understanding

Paper • 2602.06139 • Published Feb 5 • 12

Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations

Paper • 2602.05885 • Published Feb 5 • 28

Context Forcing: Consistent Autoregressive Video Generation with Long Context

Paper • 2602.06028 • Published Feb 5 • 36

authored a paper about 1 month ago

Training Data Efficiency in Multimodal Process Reward Models

Paper • 2602.04145 • Published Feb 4 • 76

upvoted 3 papers about 1 month ago

Reinforced Attention Learning

Paper • 2602.04884 • Published Feb 4 • 28

Steering LLMs via Scalable Interactive Oversight

Paper • 2602.04210 • Published Feb 4 • 18

Training Data Efficiency in Multimodal Process Reward Models

Paper • 2602.04145 • Published Feb 4 • 76

authored 2 papers about 1 month ago

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Paper • 2601.22628 • Published Jan 30 • 35

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

Paper • 2602.03845 • Published Feb 3 • 26

commented a paper about 1 month ago

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

Paper • 2602.03845 • Published Feb 3 • 26 •

4

upvoted 3 papers about 1 month ago

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

Paper • 2602.03845 • Published Feb 3 • 26

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

Paper • 2602.03619 • Published Feb 3 • 26

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published Jan 30 • 109