Dr. Yunpu Ma
About Me
I develop intelligent systems that integrate memory, reasoning, and multimodal understanding to act autonomously in open-ended environments. My goal is to build foundation models and agentic systems that continually learn, collaborate, and adapt to complex real-world tasks.
I am currently a Lecturer at LMU Munich, where I work with Prof. Hinrich Schütze on agentic AI and foundation models. In parallel, I am an external research scientist at the Huawei Research Center, where I supervise PhD students on agentic AI.
I am also a group leader at the TRESP Lab and am affiliated with the Munich Center for Machine Learning (MCML). At TRESP Lab, I co-supervise PhD students with Prof. Volker Tresp and Prof. Thomas Seidl. Before joining LMU, I was a research scientist at Siemens, working on quantum machine learning for industrial applications.
Beyond these roles, I collaborate with academic and industrial partners including Prof. Sören Pirk, Prof. Evgeny Kharlamov, and Prof. Kristian Kersting, and supervise industry-funded PhD researchers with partners such as Siemens, Huawei, and Bosch.
I received my PhD in Computer Science from LMU Munich under the supervision of Prof. Volker Tresp. My doctoral research connected relational learning with cognition, quantum computing, and causality. Before moving into computer science, I studied theoretical physics and conducted research on gauge/gravity duality at the Max Planck Institute for Physics.
My current research focuses on LLM-based multi-agent systems that communicate, coordinate, and improve through reflection and experience. I am particularly interested in agents that combine language, vision, and structured knowledge, and in translating these capabilities into robust systems for scientific and industrial applications.
