🤖 Agents | 🌍 Real-world RL | 🧬 Self-Evolution
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!
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.
-
[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.
- Languages: Python, C++, Go
- Frameworks: PyTorch, verl, Transformers, DeepSpeed
- Tools: Git, Docker, Jupyter Notebook
- Email: wuky28@mail2.sysu.edu.cn or marcowky@qq.com
- Homepage: marcowky.github.io, Github: Marcowky
- Google Scholar: Kaiyu Wu
- Location: Guangzhou, China