Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper about 19 hours ago

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Paper • 2602.08234 • Published 3 days ago • 55

upvoted a paper 3 days ago

EgoAVU: Egocentric Audio-Visual Understanding

Paper • 2602.06139 • Published 6 days ago • 11

upvoted a paper 4 days ago

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

Paper • 2602.05885 • Published 6 days ago • 28

upvoted a paper 5 days ago

Context Forcing: Consistent Autoregressive Video Generation with Long Context

Paper • 2602.06028 • Published 6 days ago • 34

authored a paper 5 days ago

Training Data Efficiency in Multimodal Process Reward Models

Paper • 2602.04145 • Published 8 days ago • 75

upvoted 2 papers 6 days ago

Reinforced Attention Learning

Paper • 2602.04884 • Published 7 days ago • 25

Steering LLMs via Scalable Interactive Oversight

Paper • 2602.04210 • Published 8 days ago • 17

upvoted a paper 7 days ago

Training Data Efficiency in Multimodal Process Reward Models

Paper • 2602.04145 • Published 8 days ago • 75

authored 2 papers 7 days ago

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Paper • 2601.22628 • Published 13 days ago • 34

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

Paper • 2602.03845 • Published 8 days ago • 24

commented a paper 8 days ago

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

Paper • 2602.03845 • Published 8 days ago • 24 •

4

upvoted 2 papers 8 days ago

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

Paper • 2602.03845 • Published 8 days ago • 24

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

Paper • 2602.03619 • Published 8 days ago • 25

upvoted a paper 9 days ago

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

Paper • 2601.22975 • Published 12 days ago • 95

upvoted a paper 10 days ago

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Paper • 2601.22628 • Published 13 days ago • 34

submitted a paper to Daily Papers 10 days ago

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Paper • 2601.22628 • Published 13 days ago • 34

upvoted 2 papers 14 days ago

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

Paper • 2601.18724 • Published 16 days ago • 7

A Pragmatic VLA Foundation Model

Paper • 2601.18692 • Published 16 days ago • 46

published a Space 19 days ago

Running

2

Efficient Reasoning Online Judgement

📉

2

updated a Space 19 days ago

Running

2

Efficient Reasoning Online Judgement

📉

2