Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper about 7 hours ago

Programmable World Model

Paper • 2609.10540 • Published 1 day ago • 38

upvoted a paper 2 days ago

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

Paper • 2609.03241 • Published 7 days ago • 89

upvoted 2 papers 3 days ago

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Paper • 2609.05295 • Published 6 days ago • 12

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published 7 days ago • 15

upvoted a paper 6 days ago

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published 9 days ago • 117

submitted a paper to Daily Papers 6 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 7 days ago • 176

upvoted a paper 6 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 7 days ago • 176

upvoted 2 papers 7 days ago

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

Paper • 2608.29846 • Published 11 days ago • 16

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

Paper • 2609.00638 • Published 9 days ago • 72

upvoted a paper 8 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 9 days ago • 486

upvoted a paper 9 days ago

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

Paper • 2608.31046 • Published 10 days ago • 149

upvoted a paper 10 days ago

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

Paper • 2608.26582 • Published 14 days ago • 45

upvoted a paper 13 days ago

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published 14 days ago • 83

authored a paper 20 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 21 days ago • 275

commented a paper 20 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 21 days ago • 275 •

2

upvoted a paper 20 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 21 days ago • 275

upvoted a paper 21 days ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published 22 days ago • 52

upvoted a paper 24 days ago

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

Paper • 2608.14277 • Published 27 days ago • 35

upvoted a paper 30 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published Aug 10 • 119

upvoted a paper about 1 month ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 517