Haoqin Tu

发表论文 37 篇 · 总被引 1013 次 · h-index 14

代表论文

• SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models (2025 · Trans. Mach. Learn. Res. · 被引 224)
• STAR-1: Safer Alignment of Reasoning LLMs with 1K Data (2025 · AAAI Conference on Artificial Intelligence · 被引 60)
• MetaClaw: Just Talk - An Agent That Meta-Learns and Evolves in the Wild (2026 · arXiv.org · 被引 21)
• ViLBench: A Suite for Vision-Language Process Reward Modeling (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 21)
• SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards (2025 · arXiv.org · 被引 20)
• Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw (2026 · arXiv.org · 被引 17)