Chengsong Huang

ChengsongHuang's activity

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

authored a paper about 8 hours ago

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published about 22 hours ago • 17

upvoted a paper about 13 hours ago

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published about 22 hours ago • 17

submitted a paper to Daily Papers about 13 hours ago

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published about 22 hours ago • 17

authored a paper 1 day ago

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Paper • 2601.03986 • Published 2 days ago • 29

upvoted a paper 1 day ago

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Paper • 2601.03986 • Published 2 days ago • 29

submitted a paper to Daily Papers 1 day ago

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Paper • 2601.03986 • Published 2 days ago • 29

upvoted a paper 1 day ago

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

Paper • 2601.03193 • Published 3 days ago • 38

upvoted a paper 3 days ago

Recursive Language Models

Paper • 2512.24601 • Published 10 days ago • 46

upvoted 2 papers 4 days ago

Diversity or Precision? A Deep Dive into Next Token Prediction

Paper • 2512.22955 • Published 12 days ago • 7

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

Paper • 2512.24615 • Published 9 days ago • 104

updated a collection 7 days ago

RelayLLM

Collection

RelayLLM • 2 items • Updated 7 days ago

updated a model 7 days ago

HINT-lab/RelayLLM-1.7B-Difficulty-Aware

2B • Updated 7 days ago • 12

published a model 7 days ago

HINT-lab/RelayLLM-1.7B-Difficulty-Aware

2B • Updated 7 days ago • 12

updated a model 7 days ago

HINT-lab/RelayLLM-1.7B-Simple

2B • Updated 7 days ago • 9

published a model 7 days ago

HINT-lab/RelayLLM-1.7B-Simple

2B • Updated 7 days ago • 9

upvoted a paper 15 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 23 days ago • 93

upvoted 3 papers 16 days ago

Reinforcement Learning for Self-Improving Agent with Skill Library

Paper • 2512.17102 • Published 22 days ago • 32

MemEvolve: Meta-Evolution of Agent Memory Systems

Paper • 2512.18746 • Published 19 days ago • 28

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Paper • 2512.19673 • Published 18 days ago • 61