Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper about 1 hour ago

Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

Paper • 2605.30852 • Published 4 days ago • 3

upvoted a paper about 12 hours ago

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models

Paper • 2605.18879 • Published 13 days ago • 6

upvoted a paper 4 days ago

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published 6 days ago • 81

upvoted a paper 5 days ago

Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling

Paper • 2605.27030 • Published 7 days ago • 29

upvoted a paper 6 days ago

Language Models Need Sleep

Paper • 2605.26099 • Published 8 days ago • 11

upvoted a paper 8 days ago

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published 11 days ago • 212

upvoted 2 papers 12 days ago

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

Paper • 2605.21468 • Published 13 days ago • 49

The Unlearnability Phenomenon in RLVR for Language Models

Paper • 2605.16787 • Published 17 days ago • 6

upvoted a paper 13 days ago

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published 18 days ago • 53

upvoted a paper 21 days ago

G-Zero: Self-Play for Open-Ended Generation from Zero Data

Paper • 2605.09959 • Published 22 days ago • 17

submitted a paper to Daily Papers 21 days ago

G-Zero: Self-Play for Open-Ended Generation from Zero Data

Paper • 2605.09959 • Published 22 days ago • 17

upvoted a paper 22 days ago

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Paper • 2605.08083 • Published 25 days ago • 69

submitted a paper to Daily Papers 22 days ago

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Paper • 2605.08083 • Published 25 days ago • 69

authored 2 papers 22 days ago

Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation

Paper • 2602.03689 • Published Feb 3

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Paper • 2605.05566 • Published 26 days ago • 37

upvoted a paper 23 days ago

SkillOS: Learning Skill Curation for Self-Evolving Agents

Paper • 2605.06614 • Published 26 days ago • 46

upvoted a paper 24 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published about 1 month ago • 119

upvoted a paper 25 days ago

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Paper • 2605.05566 • Published 26 days ago • 37

submitted a paper to Daily Papers 25 days ago

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Paper • 2605.05566 • Published 26 days ago • 37

upvoted a paper about 1 month ago

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published Apr 28 • 273