Kolja Bauer

koljabauer.bsky.social

14 April 2026 10:16

Do we really need pixel generation to model motion? 🤔 We show how directly representing motion in a compact space enables efficient, scalable planning. 10,000× faster than video models, enabling planning and reasoning in open-world and robotics settings. Check it out ⬇️

Johannes Schusterbauer

joh-schb.bsky.social

18 October 2025 10:05

🤔 What if you could generate an entire image using just one continuous token? 💡 It works if we leverage a self-supervised representation! Meet RepTok🦎: A generative model that encodes an image into a single continuous latent while keeping realism and semantics. 🧵 👇

Stefan Baumann

stefanabaumann.bsky.social

17 October 2025 10:11

🤔 What happens when you poke a scene — and your model has to predict how the world moves in response? We built the Flow Poke Transformer (FPT) to model multi-modal scene dynamics from sparse interactions. It learns to predict the 𝘥𝘪𝘴𝘵𝘳𝘪𝘣𝘶𝘵𝘪𝘰𝘯 of motion itself 🧵👇

Sander Dieleman

sedielem.bsky.social

28 July 2025 21:02

Great blog post on rotary position embeddings (RoPE) in more than one dimension, with interactive visualisations, a bunch of experimental results, and code!

Dima Damen @ECCV 2026

dimadamen.bsky.social

30 June 2025 05:42

I gave two talks @cvprconference.bsky.social #cvpr2025 Slides are now available for those interested 1- Catch me if you can: Manoeuvre the Competition with Your Unique Abilities tinyurl.com/StandOut-DD2... 2- Beyond Long Video Understanding tinyurl.com/BeyondLong-D...