I am happy to share that SpotDiffusion was accepted to WACV 2025. Page: https://t.co/YkCPNa3Px0 Code: https://t.co/AJYj82peIO Paper: https://t.co/9yd2iq1AzQ SpotDiffusion is an efficient method for seamless panorama generation from text. 🧵

Say hello to DINOv3 🦖🦖🦖 A major release that raises the bar of self-supervised vision foundation models. With stunning high-resolution dense features, it’s a game-changer for vision tasks! We scaled model size and training data, but here's what makes it special 👇

Happy to share that TKG-DM, a training-free chroma key content generation diffusion model was accepted to CVPR 25. Project led by @Oguryu417 Paper: https://t.co/BpV0xFmxrP Code: https://t.co/EohvQ4qzzO

Checkout PromptMap, presented at IUI'25, a new interaction style with text-to-image models/data that allows users to freely explore a vast collection of synthetic prompts through a map-like view with semantic zoom. Paper: https://t.co/eYJ6UBHOGK Code: https://t.co/BRHQxjwjTV

I received feedback that my post about reviews not being "random" caused stress for some students. I'm sorry for that. It was meant to be empowering. Personally, I find the idea that I don't have some control over the destiny of my papers to be disheartening. If the process is

I am very happy to share that our open-access survey about diffusion models in the field of image super-resolution got accepted by #IEEE TNNLS: https://t.co/OEz3JJGnHk #images #diffusion #models #survey @stfrolov @rave78 @spalaciob

We propose a time-dependent, attention-guided masking approach that prioritizes high-attention regions first, gradually refining the entire image. This improves quality across various models. Paper: https://t.co/XkTqtW3pkh Thanks to @LuckyOwl95 @rave78 @spalaciob @DFKI

We find that important image pixels, as measured by the attention values of DINO, are more challenging to learn (higher reconstruction error).

Dynamic attention-guided diffusion accepted to #WACV2025 🎉 We challenge the common SR diffusion approach: must the entire image be updated at each step? Some regions, like faces, may need more focus than plain backgrounds. 🧵

Check out our project page and paper for more visual results. Page: https://t.co/YkCPNa3Px0 Code: https://t.co/AJYj82peIO Paper: https://t.co/9yd2iq1AzQ Thanks to my collaborators @bmoser95 and Andreas Dengel. @DFKI @rptu_kl_ld @wacv_official

We can produce seamless panoramas much faster by leveraging the iterative nature of diffusion models and shifting non-overlapping denoising windows over time.

To generate images beyond the training resolution, MultiDiffusion averages overlapping denoising windows. While this works, it can be slow because large overlap between the windows is required.

✨🎨🏰Super excited to share our new paper Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on vLLMs 1/12

I can’t find a recent paper (and tweet) that had emojis all over an image. I think it was a method about interpreting (possibly segmenting) images with/from diffusion models. Can somebody help?

Wow that’s cool! LoRA but for training.

Thanks @_akhaliq for promoting our work! With GaLore, now it is possible to pre-train a 7B model in NVidia RTX 4090s with 24G memory! 🤔How? Instead of assuming low-rank weight structure like LoRA, we show that the weight gradient is naturally low-rank and thus can be

“Write me a scientific review in the voice of Dr. Seuss and as reviewer 2, the negative reviewer who clearly doesn’t understand the paper and has probably not read the paper. Mention that there is no novelty and that the contribution is limited.” GPT-4: Oh, I've read your work,

Vision transformers need registers! Or at least, it seems they 𝘸𝘢𝘯𝘵 some… ViTs have artifacts in attention maps. It’s due to the model using these patches as “registers”. Just add new tokens (“[reg]”): - no artifacts - interpretable attention maps 🦖 - improved performances!

When training a model, you need to make sure data loading is not your bottleneck or you're just wasting precious compute 😱 Here are some simple tests you can use to verify it 🤓

Excellent article by @sedielem about diffusion models! My favorite part is about the link to RNNs: “Diffusion models present a way to train deep RNNs without backpropagating through the recurrence at all, yielding a much more scalable training procedure.” https://t.co/IOEQGXKcuL