Ganqu Cui

发表论文 82 篇 · 总被引 13687 次 · h-index 34

代表论文

• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models (2025 · arXiv.org · 被引 402)
• TTRL: Test-Time Reinforcement Learning (2025 · Neural Information Processing Systems · 被引 217)
• A Survey of Reinforcement Learning for Large Reasoning Models (2025 · arXiv.org · 被引 160)
• A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond (2025 · arXiv.org · 被引 142)
• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe (2025 · arXiv.org · 被引 127)
• Intern-S1: A Scientific Multimodal Foundation Model (2025 · arXiv.org · 被引 81)