Moritz Reuss

Moritz is a postdoc at the Seattle Robotics Lab in Zurich, working on efficient robotic foundation models for manipulation. His research sits at the intersection of generative modeling and robot learning from demonstration data. He was a PhD student at the Karlsruhe Institute of Technology under Prof. Rudolf Lioutikov, where he worked on diffusion policies, mixture-of-experts architectures, efficient vision-language-action models, data labeling, and novel action tokenizers for robotic manipulation. His PhD was supported by the Apple Scholarship in AI/ML.
Avatar photo

Posts by Moritz Reuss

Robotics

Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models

Quick glossary for readers new to VLA/WAM terminology VLA Vision-Language-Action model: a robot policy that starts from a pretrained VLM backbone and adapts it... 61 MIN READ