Andreas Sochopoulos

Hello! My name is Andreas, and I am currently a PhD student at the University of Edinburgh (UoE), supported by Honda Research Institute Europe (HRI-EU), and advised by Sethu Vijayakumar (UoE), Michael Gienger (HRI-EU).

My research focuses on imitation learning using continuous-time generative models, such as diffusion and flow models. So far, I have worked on accelerating the inference of flow models for action generation without additional training overhead, as well as on guaranteeing constrained solutions for neural ODEs. I am particularly interested in ways to make diffusion/flow-based policies force-aware, fast, and robust when training with limited demonstrations.

I am currently exploring adaptive compliance-based VLA post-training using offline RL. If you are interested in my research or would like to discuss related topics, feel free to reach out!