Stefan Andreas Baumann
2 papers · Latest:
Computer Vision
Learning Long-term Motion Embeddings for Efficient Kinematics Generation
This paper introduces a method for efficient long-term motion generation using highly compressed learned embeddings, outperforming current video models.
2604.11737
Computer VisionEnvisioning the Future, One Step at a Time
A new autoregressive diffusion model predicts diverse future scene dynamics via sparse point trajectories, enabling fast, scalable, and accurate open-set motion.
2604.09527
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.