Chengsong Huang

ChengsongHuang's activity

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

upvoted 2 papers 5 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 6 days ago • 230

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

Paper • 2609.11115 • Published 10 days ago • 167

upvoted a paper 9 days ago

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

Paper • 2609.11499 • Published 10 days ago • 33

upvoted a paper 10 days ago

Programmable World Model

Paper • 2609.10540 • Published 11 days ago • 109

upvoted a paper 11 days ago

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

Paper • 2609.03241 • Published 17 days ago • 53

upvoted 2 papers 13 days ago

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Paper • 2609.05295 • Published 16 days ago • 17

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published 17 days ago • 18

upvoted a paper 16 days ago

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published 19 days ago • 118

submitted a paper to Daily Papers 16 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 17 days ago • 186

upvoted a paper 16 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 17 days ago • 186

upvoted 3 papers 17 days ago

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

Paper • 2608.29846 • Published 21 days ago • 15

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

Paper • 2609.00638 • Published 19 days ago • 65

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 19 days ago • 333

upvoted a paper 18 days ago

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

Paper • 2608.31046 • Published 20 days ago • 96

upvoted a paper 20 days ago

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

Paper • 2608.26582 • Published 24 days ago • 41

upvoted a paper 23 days ago

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published 24 days ago • 83

authored a paper 29 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published about 1 month ago • 174

commented a paper 30 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published about 1 month ago • 174 •

2

upvoted a paper 30 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published about 1 month ago • 174

upvoted a paper about 1 month ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 54