Chengsong Huang

ChengsongHuang's activity

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

authored a paper 10 days ago

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

Paper • 2610.04299 • Published Oct 3 • 49

liked a model 14 days ago

hyz317/HairDeck

Image-to-3D • Updated 9 days ago • 3.87k • 72

upvoted a paper 14 days ago

HairDeck: Animation-Ready Stylized Hair Cards from a Single Image

Paper • 2610.40599 • Published 16 days ago • 35

upvoted a paper 15 days ago

WebAnything: From the Wild Web to Scalable Agent Environments

Paper • 2610.37786 • Published 18 days ago • 19

upvoted a paper 16 days ago

DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models

Paper • 2610.35201 • Published 19 days ago • 15

upvoted a paper 22 days ago

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper • 2610.30926 • Published 22 days ago • 29

upvoted 2 papers 23 days ago

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Paper • 2610.26828 • Published 26 days ago • 71

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

Paper • 2610.27450 • Published 25 days ago • 15

upvoted a paper 24 days ago

Harness Self-Evolution for Long-Horizon Terminal Agents

Paper • 2610.27435 • Published 25 days ago • 11

upvoted a paper 25 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 29 days ago • 49

upvoted a paper 28 days ago

Self-Evolving Agent Harness

Paper • 2610.18813 • Published Oct 13 • 68

upvoted a paper 29 days ago

Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine

Paper • 2610.22192 • Published 30 days ago • 31

upvoted 8 papers about 1 month ago

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published Oct 9 • 69

ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents

Paper • 2610.13395 • Published Oct 9 • 46

nanoMuse: An Open-Source Personal Agent for Every Device You Own

Paper • 2610.08699 • Published Oct 6 • 104

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

Paper • 2610.04299 • Published Oct 3 • 49

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

Paper • 2610.04109 • Published Oct 2 • 21

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published Oct 2 • 38

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published Sep 30 • 134

On the Off-Policy Teacher in On-Policy Distillation

Paper • 2609.38360 • Published Sep 29 • 19