Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper 1 day ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 3 days ago • 173

upvoted a paper 2 days ago

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

Paper • 2609.22086 • Published 6 days ago • 29

upvoted a paper 8 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 10 days ago • 243

upvoted a paper 9 days ago

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

Paper • 2609.11115 • Published 14 days ago • 173

upvoted a paper 12 days ago

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

Paper • 2609.11499 • Published 14 days ago • 33

upvoted a paper 13 days ago

Programmable World Model

Paper • 2609.10540 • Published 15 days ago • 113

upvoted a paper 15 days ago

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

Paper • 2609.03241 • Published 21 days ago • 54

upvoted 2 papers 16 days ago

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Paper • 2609.05295 • Published 20 days ago • 17

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published 21 days ago • 19

upvoted 2 papers 19 days ago

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published 23 days ago • 119

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 21 days ago • 187

upvoted 2 papers 20 days ago

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

Paper • 2608.29846 • Published 25 days ago • 15

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

Paper • 2609.00638 • Published 23 days ago • 66

upvoted a paper 21 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 23 days ago • 352

upvoted a paper 22 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 24 days ago • 97

upvoted a paper 23 days ago

J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data

Paper • 2608.26582 • Published 28 days ago • 41

upvoted a paper 26 days ago

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published 28 days ago • 84

upvoted 3 papers about 1 month ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 175

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 54

SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning

Paper • 2608.14277 • Published Aug 14 • 36