Images (or image patches) are secretly multi-channel signals over groups. Below, the dihedral group of order 8: reflecting/rotating the image permutes the values in the magenta vector. So we can reshape the image into 8-tuples that all permute according to the dihedral group (edge case diagonals).

Nice LLM generated citation found by @davnords.bsky.social. I wonder who M. Lindberg and A. Andersson are...

The opportunities and risks of the entry of LLMs into mathematical research in one screenshot. I think it is clear that LLMs will make trained researchers more effective. But they will also lead to a flood of bad/wrong papers, and I'm not sure we have the tools to deal with this.

A simple argument for equivariance at scale: 1) At scale, token-wise linear layers dominate compute. 2) Token-wise linear equivariant layers implemented in the Fourier domain are block-diagonal and hence fast.

Towards the Next Generation of 3D Reconstruction @parskatt.bsky.social PhD Thesis. tl;dr: would be useful in teaching image matching - nice explanations. (too) Fancy and stylish notation. Cool Ack section and cover image. liu.diva-portal.org/smash/record...

Going to recycle an extension of this thread, but to uncertainty principles: The idea here was that almost all the listed objects arise from choosing a specific operator encoding a structure of interest (a symmetry, a statistic, a geometry, or dynamics) and then seeking its eigenfunctions. [+]

Badness is an underrated word for loss functions

These funny layernorm (and layerscale) weight values are present in early DINOv3 layers as they were in DINOv2 by the way :)

Have you ever asked yourself how much your favorite vision model knows about image capture parameters (e.g., the amount of JPEG compression, the camera model, etc.)? Furthermore, could these parameters influence its semantic recognition abilities?

Introducing DINOv3 🦕🦕🦕 A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters👇

Academic Articles Assessed In-silico (AAAI).

EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅 EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu eurips.cc

Presented with my co-supervisor @bokmangeorg.bsky.social at #ICML25, fun time!

Tomorrow at ICML [Tuesday 4:30 pm, poster W-213] @davnords.bsky.social and I will present our spotlighted flop paper. Come by and let us try to convince you that equivariant nets should be standard in vision tasks due to computational benefits! bsky.app/profile/bokm...

I'm @ ICML, see you there :)

> (3189 additional authors not shown) ...jfc google.

The sycophantic tone of ChatGPT always sounded familiar, and then I recognized where I'd heard it before: author response letters to reviewer comments. "You're exactly right, that's a great point!" "Thank you so much for this insight!" Also how it always agrees even when it contradicts itself.

We just released COLMAP v3.12, which adds long-awaited, end-to-end support for multi-camera rigs and 360° panoramas 👀 COLMAP just got better at handling your robotics, AR/VR, or 360 data - try it yourself and let us know! github.com/colmap/colma... Kudos to Johannes & team for this great work 🚀

Dense Match Summarization for Faster Two-view Estimation Jonathan Astermark, Anders Heyden, Viktor Larsson tl;dr: use clustering to reduce RANSAC time when using dense methods like RoMa. Kudos for eval on WxBS. P.S. now the same, but for BA? arxiv.org/abs/2506.028...

UFM: A Simple Path towards Unified Dense Correspondence with Flow Yuchen Zhang et 11 al tl;dr: wide-baseline and optical flow data help each other. DINO layer selection. No matching, just flow regression with RoMA- loss. A LOT of ablations arxiv.org/abs/2506.09278 1/

And today I'm presenting this work at #CVPR2025! 🗓️ Date: 16:00-18:00, Fri, Jun 13 (Today) 📍Place: Poster #115 in Session 2 (ExHall D) 💻 Code: github.com/ericssonrese...

Reminder that the MSCA postdoctoral program exists. If you have a PhD and want to work in a European lab, you have until September to apply. Just contact them now. ec.europa.eu/info/funding...

Our recent paper on universality classes of equivariant networks arxiv.org/abs/2506.02293 enjoyed being part of it (and more to come!).

The war on science in the US is already having an effect on private sector research like AlphaFold. Bears repeating but the private sector builds on top of things created by academic research for the public good. This hurts everyone.

We're having a fun time with equivariance and modern vision architectures.

"Can it be read in the morning?"

Apparently AI in Danish is "kunstig intelligens", which sounds like "weird intelligence" in Swedish ("konstig intelligens").

What is mathematical beauty? tug.org/books/review...

I got the best teaching evals of my career for a large course last semester— along with three teaching awards— after rebuilding my intro class around in-class handwritten essays. I simply do not believe that this is unsolvable or that students don't care about actually learning to do their work.

This is an incredible story. Extremely well written deep dive into an entire generation captured by generative AI. Even professors are using AI to grade AI written papers. Wild.

How does perspective work in art and photography? In a new paper, we describes experiments suggesting answers to age-old questions about how people perceive perspective. 1/ #VisionScience
#Art #ArtHistory www.nature.com/articles/s41...

Finally a comprehensive paper on neural networks with non-linear equivariant maps arxiv.org/abs/2504.20974

Amen

4yrs ago, the Geometric Deep Learning proto-book hit the arXiv 📚 Today, we proudly release *Chapter 4* of the GDL Book! 📖 Wrapping up foundations, exceeding the proto-book page count 🚀 Next: deep-dives into the 5 Gs! #⃣🔁🕸️🌐🪢 @mmbronstein.bsky.social @joanbruna.bsky.social @taco-cohen.bsky.social

Bach with the "evil" interval tritone down on the word hypocrisy.

Need Equivariance and Fast? 🚀 Try PASSION Lab's OpenEquivariance Library! github.com/vbharadwaj-b... This drop-in library produces the same results as the e3nn library in a fraction of the cost! See their SIAM preprint for details: arxiv.org/abs/2501.13986

Registration for this years CHAIR Structured Learning Workshop is open. Speakers include: Klaus Robert Müller, Jens Sjölund, @alextong.bsky.social , @janstuehmer.bsky.social, @arnauddoucet.bsky.social, @marcocuturi.bsky.social , Marta Betcke, Elena Agliari, Beatriz Seoane, Alessandro Ingrosso

If you are at ICLR, you should chat with Marco about their work (sorry for just screenshotting a tweet) arxiv.org/abs/2406.08966 poster 188. I like how much of a clean and deep thinker he is. He might also be looking for positions soon.

llmao

Summarized my thoughts on #ICLR2025 LLM experiment for improving review quality, in a blog post I was initially planning to make a few posts here, but the content turned out to be longer than I expected Share your thought in the blog post (URLs in the next post) or reply here🤗

Computer vision researcher Suguru Onda just had his US visa revoked. x.com/adamsmallksl...

New blog post: let's talk about latents! sander.ai/2025/04/15/l...

1. LLM-generated code tries to run code from online software packages. Which is normal but 2. The packages don’t exist. Which would normally cause an error but 3. Nefarious people have made malware under the package names that LLMs make up most often. So 4. Now the LLM code points to malware.

I have accepted the review request It felt like the right thing to do I know You will hate me. (Letter to my future self)

Industry PhD opportunity: together with AstraZeneca, we’re recruiting an industial PhD student in data-driven life sciences to join us here in Gothenburg, SE! Deadline to apply April 24. More info in ad: www.scilifelab.se/career/indus...

We are recruiting a colleague to our division at Chalmers in Data-Driven Life Science (broadly defined), a competitive starting package is offered and you get to be part of a support, yet young and ambitious research environment. Apply here: www.chalmers.se/en/about-cha...

We have just opened a fully-funded PhD position at Cambridge, supervised by me & Vasily Belokurov. Topic: AI + astronomical imaging (broadly defined). Deadline: April 16. Please share with anyone who may be interested! www.postgraduate.study.cam.ac.uk/courses/dire...

In addition to not being able to solve hard math problems, LLMs can't grade solutions either.

#IMC2025 @cvprconference.bsky.social challenge is online! This year: - back to collection_mapping: directory with many (similar) scenes->your job to SfM & cluster them - a bit more of training set - no transparent objects $50000 prize fund Deadline: June 2 www.kaggle.com/competitions... #IMW2025