Tim Windecker

Intern at Amazon RIVR

Welcome — here you can find a brief overview of my background and experience. Feel free to explore and get in touch if you want to discuss anything!

About Me

Portrait of me

I'm a recent Master's graduate and ICRA author working at the intersection of Foundation Models and Robotics. My focus is on Vision-Language-Action (VLA) architectures and visual grounding, with the goal of advancing embodied AI.

I completed my Bachelor's and Master's degrees in Informatics at the Karlsruhe Institute of Technology (KIT). During my studies, I conducted my Master's thesis at ETH Zurich's Robotic Systems Lab (RSL) and spent two exchange semesters at the University of Skövde in Sweden. I also gained hands-on experience deploying and evaluating VLA systems at KIT's Intuitive Robots Lab (IRL), where I worked for almost 2 years.

My Skills

Multimodal Foundation Models Multimodal Evaluation & Benchmarking Teleoperation & Data Collection Python ML Frameworks C++, C

Selected Projects

NaviTrace overview

NaviTrace: Evaluating Embodied Navigation of Vision-Language Models

NaviTrace is a novel VQA benchmark for VLMs that evaluates models on their embodiment-specific understanding of navigation across challenging real-world scenarios.

Tim Windecker, Manthan Patel, Moritz Reuss, Richard Schwarzkopf, Cesar Cadena, Rudolf Lioutikov, Marco Hutter, Jonas Frey
— IEEE International Conference on Robotics and Automation 2026 (ICRA)

Get in Touch

Got an idea or want to discuss a problem? Please reach out and let me know.