Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper 1 day ago

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

Paper • 2512.07461 • Published 3 days ago • 61

upvoted 3 papers 2 days ago

AI & Human Co-Improvement for Safer Co-Superintelligence

Paper • 2512.05356 • Published 6 days ago • 8

Self-Improving VLM Judges Without Human Annotations

Paper • 2512.05145 • Published 8 days ago • 15

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Paper • 2512.02580 • Published 9 days ago • 27

upvoted a paper 8 days ago

Guided Self-Evolving LLMs with Minimal Human Supervision

Paper • 2512.02472 • Published 9 days ago • 48

commented a paper 8 days ago

Guided Self-Evolving LLMs with Minimal Human Supervision

Paper • 2512.02472 • Published 9 days ago • 48 •

2

upvoted a paper 11 days ago

Video Generation Models Are Good Latent Reward Models

Paper • 2511.21541 • Published 14 days ago • 45

upvoted a paper 13 days ago

Latent Collaboration in Multi-Agent Systems

Paper • 2511.20639 • Published 15 days ago • 113

upvoted a paper 14 days ago

Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

Paper • 2511.19900 • Published 16 days ago • 46

upvoted 2 papers 16 days ago

Insights from the ICLR Peer Review and Rebuttal Process

Paper • 2511.15462 • Published 21 days ago • 6

SAM 3: Segment Anything with Concepts

Paper • 2511.16719 • Published 20 days ago • 109

upvoted 2 papers 19 days ago

Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning

Paper • 2511.16043 • Published 21 days ago • 105

Step-Audio-R1 Technical Report

Paper • 2511.15848 • Published 21 days ago • 51

upvoted 2 papers 20 days ago

SAM 3D: 3Dfy Anything in Images

Paper • 2511.16624 • Published 20 days ago • 106

First Frame Is the Place to Go for Video Content Customization

Paper • 2511.15700 • Published 21 days ago • 52

updated a collection 20 days ago

VLM

Collection

14 items • Updated 20 days ago

authored a paper 21 days ago

VisPlay: Self-Evolving Vision-Language Models from Images

Paper • 2511.15661 • Published 21 days ago • 42

commented a paper 21 days ago

VisPlay: Self-Evolving Vision-Language Models from Images

Paper • 2511.15661 • Published 21 days ago • 42 •

3

upvoted a paper 21 days ago

VisPlay: Self-Evolving Vision-Language Models from Images

Paper • 2511.15661 • Published 21 days ago • 42

upvoted a paper 22 days ago

P1: Mastering Physics Olympiads with Reinforcement Learning

Paper • 2511.13612 • Published 23 days ago • 132