Topic: flow models

Develop generative modelling methods, scalable training algorithms and foundation-model technologies in Charlotte Bunne’s Artificial Intelligence in Molecular Medicine Lab. Research directions include diffusion and flow models, multimodal representation learning, efficient adaptation and AI for scientific discovery. The appointment provides dedicated access to CSCS and Swiss AI Initiative computing. Biomedical experience is not required. The preferred start is autumn 2026, with later dates by arrangement.

Diffusion and flow models provide expressive distributions over continuous actions in robotic control. This talk explains how modelling extended action sequences improved imitation learning and subsequently offline and offline-to-online reinforcement learning. It reviews algorithms built around these representations and large-scale control models that use them, connecting policy expressiveness with practical learning performance.