Chengsong Huang

ChengsongHuang's activity

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

upvoted 2 papers 4 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 5 days ago • 225

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

Paper • 2609.11115 • Published 9 days ago • 164

upvoted a paper 8 days ago

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

Paper • 2609.11499 • Published 9 days ago • 33

upvoted a paper 9 days ago

Programmable World Model

Paper • 2609.10540 • Published 10 days ago • 109

upvoted a paper 10 days ago

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

Paper • 2609.03241 • Published 16 days ago • 53

upvoted 2 papers 12 days ago

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Paper • 2609.05295 • Published 15 days ago • 17

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published 16 days ago • 17

upvoted 2 papers 15 days ago

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published 18 days ago • 118

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 16 days ago • 186

upvoted 3 papers 16 days ago

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

Paper • 2608.29846 • Published 20 days ago • 15

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

Paper • 2609.00638 • Published 18 days ago • 65

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 18 days ago • 333

upvoted a paper 17 days ago

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

Paper • 2608.31046 • Published 19 days ago • 95

upvoted a paper 19 days ago

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

Paper • 2608.26582 • Published 23 days ago • 41

upvoted a paper 22 days ago

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published 23 days ago • 83

upvoted a paper 29 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 30 days ago • 174

upvoted a paper 30 days ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published about 1 month ago • 54

upvoted 2 papers about 1 month ago

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

Paper • 2608.14277 • Published Aug 14 • 36

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published Aug 10 • 119

upvoted a paper about 2 months ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 522