Diffusion models treat every part of an image equally. → Same number of steps. Same compute. But images aren’t uniform. 🤔 Some regions are easy, others are hard. So why force the model to treat them the same? 🧵
CompVis - Computer Vision and Learning LMU Munich
@compvis.bsky.social
Computer Vision and Learning research group @ LMU Munich, headed by Björn Ommer. Generative Vision (Stable Diffusion, VQGAN) & Representation Learning 🌐 https://ommer-lab.com
Six papers from CompVis @ LMU accepted to #CVPR2026! Looking forward to presenting, catching up with folks whose work we've been reading all year, and seeing what the rest of the community is up to. If you're there, come find us! Paper threads 👇
Empfehlungen der KI-Kommission des Bundesministerium für Wirtschaft und Energie: kikommission.de #KIKommission #KI #StableDiffusion #Innovation #LMU #BMWE #Wettbewerb #DigitaleSouveränität
🎬 “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
Prof. Björn Ommer: How AI can transform society if we use it responsibly
YouTube video by MCML_Munich Center for Machine Learning
youtu.be
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. 🧵👇
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
Excited to share that we'll be presenting four papers at the main conference at ICCV 2025 this week! Come say hi in Honolulu! 👋 Pingchuan, Ming, Felix, Stefan, Timy, and Björn Ommer will be attending.
🎉 From @elsa-ai.eu: 15 new members join the European Lighthouse on Secure & Safe AI—expanding reach across Europe and deepening ties with the @ellis.eu ecosystem. Everything you need to know 👉 elsa-ai.eu/elsa-welcome...
Fascinating approach — encoding an entire image into a single continuous latent token via self-supervised representation learning. RepTok 🦎 highlights how compact generative representations can retain both realism and semantic structure.
Johannes Schusterbauer@joh-schb.bsky.social · 10mo ago🤔 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. 🧵 👇
🤔 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 🧵👇
𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗳𝘂𝗹𝗹𝘆 𝗳𝘂𝗻𝗱𝗲𝗱 𝗣𝗵𝗗 𝗣𝗼𝘀𝗶𝘁𝗶𝗼𝗻𝘀: We are offering several PhD positions across our various research areas, open to highly qualified candidates. ‼️ The application portal will be open from 15 October to 14 November 2025. Find out more: mcml.ai/opportunitie...
🎧 ELLIOT on the airwaves! How do we build open and trustworthy AI in Europe? 🎙️ In a recent radio interview, Luk Overmeire from VRT shared insights on ELLIOT, #FoundationModels and the role of public broadcasters in shaping human-centred AI. 📻 Interview in Dutch: mimir.mjoll.no/shares/JRqlO...
"What makes us human in an AI-shaped world?" — At #MCML Munich AI Day 2025, Neil Lawrence explored this question, reminding us of the indivisible human core machines can't replicate. Björn Ommer followed with insights into how GenAI is commodifying intelligence and reshaping how we use computers.
🎉 The ELLIOT project Kick-off Meeting was successfully hosted by CERTH-ITI, in Thessaloniki! 🏛️ 30 partners from 12 countries 🌍 launched this exciting journey to advance open, trustworthy AI and #FoundationModels across Europe. 🤖 Stay tuned for more updates on #AIresearch and #TrustworthyAI! 💡
🧹 CleanDiFT: Diffusion Features without Noise @rmsnorm.bsky.social*, @stefanabaumann.bsky.social*, @koljabauer.bsky.social*, @frankfundel.bsky.social, Björn Ommer Oral Session 1C (Davidson Ballroom): Friday 9:00 Poster Session 1 (ExHall D): Friday 10:30-12:30, # 218 compvis.github.io/cleandift/
CleanDIFT: Diffusion Features without Noise
CleanDIFT enables extracting Noise-Free, Timestep-Independent Diffusion Features
compvis.github.io
🎉 Excited to share that our lab has three papers accepted at CVPR 2025! Come say hi in Nashville! 👋 Johannes, Ming, Kolja, Stefan, and Björn will be attending.
📢 ELLIOT is coming! A €25M #HorizonEurope project to develop open, trustworthy Multimodal Generalist Foundation Models, #MGFM, for real-world applications. Starting July, it brings 30 partners from 12 countries to shape Europe’s #AI future. 🔍 Follow for updates on #OpenScience & #FoundationModels.
🎉 Excited to share that our lab has three papers accepted at CVPR 2025! Come say hi in Nashville! 👋 Johannes, Ming, Kolja, Stefan, and Björn will be attending.
If you are interested, feel free to check the paper (arxiv.org/abs/2506.02221) or come by at CVPR: 📌 Poster Session 6, Sunday 4:00 to 6:00 PM, Poster #208
Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM mode...
arxiv.org
Grand Opening of the AI-HUB@LMU. The AI-HUB@LMU is a platform that for the first time unites all 18 faculties of the #LMU as a joint scientific community. 📅January 29, 2025, 6:00 PM 📍 Große Aula, LMU Munich Full program here: www.ai-news.lmu.de/grand-openin...
www.stuttgarter-nachrichten.de/inhalt.kuens...
Künstliche Intelligenz: Experte: Stehen erst am Beginn der KI-Entwicklung
Der Informatiker Björn Ommer ist bekannt für seine bahnbrechenden Arbeiten im Bereich der KI. Auf der Konferenz DLD sagt er große Auswirkungen durch KI auch für kleinere Unternehmen voraus.
stuttgarter-nachrichten.de
Attending my first corporate-sponsored business conference: there’s a live band playing between talks to keep the energy up. Meanwhile, academic conferences are struggling to afford coffee breaks. Want this for EPSA! @compvis.bsky.social
🤔When combining Vision-language models (VLMs) with Large language models (LLMs), do VLMs benefit from additional genuine semantics or artificial augmentations of the text for downstream tasks? 🤨Interested? Check out our latest work at #AAAI25: 💻Code and 📝Paper at: github.com/CompVis/DisCLIP 🧵👇
Did you know you can distill the capabilities of a large diffusion model into a small ViT? ⚗️ We showed exactly that for a fundamental task: semantic correspondence📍 A thread 🧵👇
🤔 Why do we extract diffusion features from noisy images? Isn’t that destroying information? Yes, it is - but we found a way to do better. 🚀 Here’s how we unlock better features, no noise, no hassle. 📝 Project Page: compvis.github.io/cleandift 💻 Code: github.com/CompVis/clea... 🧵👇
