← authors · overview

• Group Sequence Policy Optimization
  2025 · 453 citations
• Qwen3 Technical Report
  2025 · 73 citations
• The Expressive Power of Graph Neural Networks: A Survey
  2023 · 4 citations
• Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
  2025 · 1 citations
• CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
  2026
• Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
  2026
• Learning complete and explainable visual representations from itemized text supervision
  2025
• Soft Adaptive Policy Optimization
  2025
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
  2025
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
  2025
• Group Sequence Policy Optimization
  2025
• GRACE: Generative Representation Learning via Contrastive Policy Optimization
  2025
• Soft Adaptive Policy Optimization
  2025
• From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
  2025
• TeleChat Technical Report
  2024