Chengsong Huang

ChengsongHuang's activity

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

upvoted 2 papers 6 days ago

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

Paper • 2610.30926 • Published 6 days ago • 204

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

Paper • 2610.26828 • Published 10 days ago • 102

upvoted 2 papers 7 days ago

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

Paper • 2610.27450 • Published 9 days ago • 24

Harness Self-Evolution for Long-Horizon Terminal Agents

Paper • 2610.27435 • Published 9 days ago • 14

upvoted a paper 8 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 13 days ago • 57

upvoted a paper 12 days ago

Self-Evolving Agent Harness

Paper • 2610.18813 • Published 16 days ago • 103

upvoted a paper 13 days ago

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

Paper • 2610.22192 • Published 14 days ago • 41

upvoted a paper 15 days ago

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 20 days ago • 126

upvoted a paper 17 days ago

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

Paper • 2610.13395 • Published 20 days ago • 56

upvoted a paper 20 days ago

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

Paper • 2610.08699 • Published 23 days ago • 122

upvoted a paper 21 days ago

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

Paper • 2610.04299 • Published 26 days ago • 86

upvoted a paper 22 days ago

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

Paper • 2610.04109 • Published 27 days ago • 35

upvoted a paper 24 days ago

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published 27 days ago • 107

upvoted a paper 27 days ago

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

Paper • 2609.38721 • Published 29 days ago • 227

upvoted a paper 28 days ago

On the Off-Policy Teacher in On-Policy Distillation

Paper • 2609.38360 • Published 30 days ago • 24

upvoted 3 papers 29 days ago

TabFM: A Zero-Shot Foundation Model for Tabular Data

Paper • 2609.37959 • Published 30 days ago • 21

Adversarial Training for Pixel Diffusion

Paper • 2609.38170 • Published 30 days ago • 22

TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs

Paper • 2609.33589 • Published Sep 27 • 9

upvoted 2 papers about 1 month ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published Sep 25 • 121

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published Sep 21 • 221