Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper 3 days ago

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

Paper • 2610.08699 • Published 6 days ago • 101

upvoted a paper 4 days ago

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

Paper • 2610.04299 • Published 9 days ago • 70

upvoted a paper 5 days ago

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

Paper • 2610.04109 • Published 10 days ago • 35

upvoted a paper 7 days ago

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published 10 days ago • 103

upvoted a paper 10 days ago

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

Paper • 2609.38721 • Published 12 days ago • 274

upvoted a paper 11 days ago

On the Off-Policy Teacher in On-Policy Distillation

Paper • 2609.38360 • Published 13 days ago • 24

upvoted 3 papers 12 days ago

TabFM: A Zero-Shot Foundation Model for Tabular Data

Paper • 2609.37959 • Published 13 days ago • 21

Adversarial Training for Pixel Diffusion

Paper • 2609.38170 • Published 13 days ago • 22

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

Paper • 2609.33589 • Published 15 days ago • 9

upvoted a paper 14 days ago

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

Paper • 2609.31620 • Published 17 days ago • 145

upvoted 2 papers 20 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 21 days ago • 227

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Paper • 2609.22086 • Published 24 days ago • 34

upvoted 2 papers 27 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 28 days ago • 251

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Paper • 2609.11115 • Published Sep 10 • 174

upvoted 6 papers about 1 month ago

Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs

Paper • 2609.11499 • Published Sep 10 • 33

Programmable World Model

Paper • 2609.10540 • Published Sep 9 • 95

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Paper • 2609.03241 • Published Sep 3 • 51

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Paper • 2609.05295 • Published Sep 4 • 19

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published Sep 3 • 20

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published Sep 1 • 121