Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains prohibitively inefficient. We model scene dynamics orders of magnitude more efficiently by directly operating on a long-term motion embedding that is learned from large-scale trajectories obtained from tracker models. This enables efficient generation of long, realistic motions that fulfill goals specified via text prompts or spatial pokes. To achieve this, we first learn a highly compressed motion embedding with a temporal compression factor of 64x. In this space, we train a conditional flow-matching model to generate motion latents conditioned on task descriptions. The resulting motion distributions outperform those of both state-of-the-art video models and specialized task-specific approaches.
@article{arxiv.2604.11737,
title = {Learning Long-term Motion Embeddings for Efficient Kinematics Generation},
author = {Nick Stracke and Kolja Bauer and Stefan Andreas Baumann and Miguel Angel Bautista and Josh Susskind and Björn Ommer},
journal= {arXiv preprint arXiv:2604.11737},
year = {2026}
}
Comments
for the project page and code, view https://compvis.github.io/long-term-motion