Hi there, I'm Kaiyu Wu (伍开钰), and I go by Marco. 👋

🤖 Agents | 🌍 Real-world RL | 🧬 Self-Evolution

Homepage GitHub Google Scholar Email

🧐 About Me

I am currently a first-year Master’s student at the School of Computer Science and Engineering, Sun Yat-sen University (SYSU), and a member of the HCP Lab, advised by Prof. Keze Wang.

🌱 Status: I am actively looking for Research Collaborations and Internship Opportunities. Feel free to reach out!

🎓 Research Interests

My primary research centers on Reinforcement Learning (RL) for Visual Language Models (VLMs) and Large Language Models (LLMs) in real-world environments.

🎯 Ultimate Goal: Enabling VLMs and LLMs to exist autonomously in the real world and achieve dynamic self-evolution.

Currently, I am focusing on GUI Agents and exploring how agents can interact more effectively with software interfaces.

📝 Selected Publications

  • [ICASSP 2026] Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology
    Kaiyu Wu, Pucheng Han, Hualong Zhang, Naigeng Wu, Keze Wang
    [Paper Link] [Code]

  • Enhancing Visual Programming for Visual Reasoning via Probabilistic Graphs
    Wentao Wan, Kaiyu Wu, Qingyang Ma, Nan Kang, Yunjie Chen, Liang Lin, Keze Wang
    [Paper Link]

For a full list of publications, please visit my Google Scholar.

🛠️ Tech Stack & Tools

  • Languages: Python, C++, Go
  • Frameworks: PyTorch, verl, Transformers, DeepSpeed
  • Tools: Git, Docker, Jupyter Notebook

💬 Connect with Me