Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper 4 days ago

SkillOrchestra: Learning to Route Agents via Skill Transfer

Paper • 2602.19672 • Published 5 days ago • 54

upvoted 2 papers 11 days ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published 11 days ago • 100

Experiential Reinforcement Learning

Paper • 2602.13949 • Published 14 days ago • 68

upvoted a paper 18 days ago

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Paper • 2602.08234 • Published 20 days ago • 67

upvoted a paper 20 days ago

EgoAVU: Egocentric Audio-Visual Understanding

Paper • 2602.06139 • Published 23 days ago • 12

upvoted a paper 21 days ago

Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations

Paper • 2602.05885 • Published 23 days ago • 28

upvoted a paper 22 days ago

Context Forcing: Consistent Autoregressive Video Generation with Long Context

Paper • 2602.06028 • Published 23 days ago • 36

upvoted 2 papers 23 days ago

Reinforced Attention Learning

Paper • 2602.04884 • Published 24 days ago • 28

Steering LLMs via Scalable Interactive Oversight

Paper • 2602.04210 • Published 25 days ago • 18

upvoted a paper 24 days ago

Training Data Efficiency in Multimodal Process Reward Models

Paper • 2602.04145 • Published 25 days ago • 76

upvoted 2 papers 25 days ago

Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

Paper • 2602.03845 • Published 25 days ago • 26

Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation

Paper • 2602.03619 • Published 25 days ago • 26

upvoted a paper 26 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 29 days ago • 106

upvoted a paper 27 days ago

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Paper • 2601.22628 • Published 30 days ago • 35

upvoted 6 papers about 1 month ago

HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences

Paper • 2601.18724 • Published Jan 26 • 7

A Pragmatic VLA Foundation Model

Paper • 2601.18692 • Published Jan 26 • 47

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 198

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge

Paper • 2601.08808 • Published Jan 13 • 39

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Paper • 2601.10355 • Published Jan 15 • 39

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published Jan 13 • 155