Kolja Bauer
@koljabauer.bsky.social
ELLIS PhD Student in Generative AI @ Ommer Lab (Stable Diffusion)
Pinned
Kolja Bauer
@koljabauer.bsky.social
· Dec 5
🤔 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...
🧵👇
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...
🧵👇
In order to extract features from diffusion models, you have to noise your input and tune the noise level for each downstream task. But isn't there a better way? 🤔
Turns out there is, using our newly proposed feature extraction method CleanDIFT 🧹🚀
Check it out ⬇️
Turns out there is, using our newly proposed feature extraction method CleanDIFT 🧹🚀
Check it out ⬇️
Reposted by Kolja Bauer
I’m thrilled to share that I’ll present two first-authored papers at #ICCV2025 🌺 in Honolulu together with @mgui7.bsky.social ! 🏝️
(Thread 🧵👇)
(Thread 🧵👇)
October 18, 2025 at 3:01 AM
I’m thrilled to share that I’ll present two first-authored papers at #ICCV2025 🌺 in Honolulu together with @mgui7.bsky.social ! 🏝️
(Thread 🧵👇)
(Thread 🧵👇)
Reposted by Kolja Bauer
🤔 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 🧵👇
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 🧵👇
October 15, 2025 at 1:56 AM
🤔 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 🧵👇
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 🧵👇
Reposted by Kolja Bauer
🤔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
🧵👇
🤨Interested? Check out our latest work at #AAAI25:
💻Code and 📝Paper at: github.com/CompVis/DisCLIP
🧵👇
January 8, 2025 at 3:54 PM
🤔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
🧵👇
🤨Interested? Check out our latest work at #AAAI25:
💻Code and 📝Paper at: github.com/CompVis/DisCLIP
🧵👇
In order to extract features from diffusion models, you have to noise your input and tune the noise level for each downstream task. But isn't there a better way? 🤔
Turns out there is, using our newly proposed feature extraction method CleanDIFT 🧹🚀
Check it out ⬇️
Turns out there is, using our newly proposed feature extraction method CleanDIFT 🧹🚀
Check it out ⬇️
🤔 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...
🧵👇
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...
🧵👇
December 5, 2024 at 7:58 AM
In order to extract features from diffusion models, you have to noise your input and tune the noise level for each downstream task. But isn't there a better way? 🤔
Turns out there is, using our newly proposed feature extraction method CleanDIFT 🧹🚀
Check it out ⬇️
Turns out there is, using our newly proposed feature extraction method CleanDIFT 🧹🚀
Check it out ⬇️
Reposted by Kolja Bauer
After many years, our lab finally has a social media presence at @compvis.bsky.social ! 🥳
Give it a follow, we have some amazing research on generative computer vision coming soon!
Give it a follow, we have some amazing research on generative computer vision coming soon!
November 20, 2024 at 6:31 PM
After many years, our lab finally has a social media presence at @compvis.bsky.social ! 🥳
Give it a follow, we have some amazing research on generative computer vision coming soon!
Give it a follow, we have some amazing research on generative computer vision coming soon!