Skip to content

Author

Sven Behnke

We have 3 of 16 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training

Text-to-motion models generate plausible human motion but do not model a robot's dynamics; whole-body tracking controllers execute robot references reliably but cannot replan an infeasible one. Recent language-to-humanoid systems bridge this gap by training. We measure how much of the gap closes with no training at all...

Raphael Memmesheimer, Sven Behnke · 0 citations
Jul 2026

ContactFlow: A video action conditioning that transfers across embodiments

This work proposes Contact Flow, an embodiment-agnostic action representation that encodes manipulation through the trajectory of 3D contact points between an actor and a target object, and integrates this model into a propose-imagine-verify-act pipeline, where generated rollouts are assessed by a vision-language model...

Sami Azirar, Enrico Pallotta, Jan Nogga et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.