Kosta Derpanis

csprofkgd.bsky.social

29 April 2026 11:57

Giving a talk soon here at @lmu.de for Björn Ommer’s group @compvis.bsky.social ❤️

Munich Center for Machine Learning

munichcenterml.bsky.social

29 April 2026 11:56

🎬 “AI should be a tool that empowers everyone, not just those with the most computing power.” #MCML PI Björn Ommer explains why democratizing AI was the driving force behind the development of Stable Diffusion. 👉 Watch the video: youtu.be/xuBRRItRmsg

Shiry Ginosar

shiryginosar.bsky.social

18 April 2026 20:58

Great to see corroborating evidence to our motion-forecasting.github.io work from other groups! Check out this concurrent great work from @stefanabaumann.bsky.social, @jannik-w.bsky.social, @tommymarto.bsky.social, Mahdi M. Kalayeh, and Björn Ommer (@compvis.bsky.social)

Nick Stracke

rmsnorm.bsky.social

14 April 2026 10:17

Video diffusion models learn motion indirectly through pixels. But motion itself is much lower-dimensional. We introduce 64× temporally compressed motion embeddings that directly capture scene dynamics. This enables efficient planning -> 10,000× faster than video models. 🧵👇

Stefan Baumann

stefanabaumann.bsky.social

13 April 2026 10:14

You don't imagine the future by mentally rendering a movie. You trace how things move -- abstractly, sparsely, step by step. We built a model that does exactly this. It predicts motion, not pixels -- and it's 3,000× faster than video world models. Myriad, accepted at @cvprconference.bsky.social