Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper 2 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 9 days ago • 115

upvoted 2 papers 3 days ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published 8 days ago • 68

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published 7 days ago • 66

upvoted a paper 8 days ago

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

Paper • 2607.05511 • Published 11 days ago • 22

upvoted a paper 10 days ago

PACE: A Proxy for Agentic Capability Evaluation

Paper • 2607.02032 • Published 15 days ago • 18

upvoted a paper 16 days ago

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Paper • 2606.28480 • Published 21 days ago • 48

upvoted 7 papers about 1 month ago

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 381

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

Paper • 2606.06087 • Published Jun 4 • 67

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

Paper • 2606.06155 • Published Jun 4 • 10

Neural Networks Provably Learn Spectral Representations for Group Composition

Paper • 2606.02993 • Published Jun 2 • 6

Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling

Paper • 2606.03102 • Published Jun 2 • 14

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

Paper • 2605.30852 • Published May 29 • 10

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models

Paper • 2605.18879 • Published May 20 • 8

upvoted 7 papers about 2 months ago

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published May 27 • 93

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

Paper • 2605.27030 • Published May 26 • 32

Language Models Need Sleep

Paper • 2605.26099 • Published May 25 • 13

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published May 22 • 257

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

Paper • 2605.21468 • Published May 20 • 51

The Unlearnability Phenomenon in RLVR for Language Models

Paper • 2605.16787 • Published May 16 • 6

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published May 15 • 53