Don't miss your chance to register for the Structured Learning Workshop, to be held October 27-28 in Gothenburg, Sweden. 🇸🇪 Amazing line-up of speakers, super excited to be hosting this event now for the 4th year here at Chalmers! Registration link and more info: chalmers.ungapped.io/Events/5f087...

2026 CHAIR Structured Learning Workshop

Welcome to the 2026 Chalmers AI Research Center Workshop for Structured Learning. In this workshop we broadly cover topics related to Structured Learning targeting specifically the following questions...

chalmers.ungapped.io

Some of the TMLR Editors in Chief are doing a meet-and-greet tomorrow at #ICML2026! July 7 at 11 AM in The Platz Come and: - discuss new policies (submission quotas, AI reviewer) - pick up stickers if you're an AE, expert reviewer, etc. - just hang out!

New preprint out on equivariant ViTs, generalizing our prior work. Led by Chih-Chun Wang (Tikun Ong) who has done an excellent job in formalizing every part of the architecture in a nice coherent manner. He is currently looking for PhD positions in Geometric DL! arxiv.org/abs/2606.27864

Got lucky with top-tier venues like #ECCV2026 or #CVPR2026? #3DV2027 will have a Nectar Track! 😎 🔎 Increase visibility 🎯 Targeted #3D audience 🌞 Mediterranean weather & lively city to decompress after major 2027 deadlines. 🗓️Mark this in your goals - info on ddls coming soon!

We are aware of the strong interest in the #ECCV2026 camera-ready instructions. Here are the key details while you wait for the Meteor submission site invite: 1/3

The alpha version of my new book "Optimal Transport for Machine Learners" is out, with in particular an online version with interactive figures www.gpeyre.com/ot4ml/

We don’t always know what problems are hard for LLMs. So devs evaluate on tasks HUMANS find hard or on broad benchmarks. What if we could instead anticipate which scenarios a model will fail on—all without evaluating specific input examples? 🧵NEW PAPER by @jenniferlumeng.bsky.social

Global Structure-from-Motion Meets Feedforward Reconstruction Linfei Pan, Johannes Schönberge, @marcpollefeys.bsky.social tl;dr: Doppelganger + π³ + intrinsics/rotation/similarity averaging + BA with FF priors arxiv.org/abs/2605.26103

Fun fact: The tetrahedron has 12 rotation symmetries - the tetrahedral group. It has 24 rotoreflection symmetries - the full tetrahedral group. But there is another 24 element rotoreflection group containing all tetrahedral rotations - the pyritohedral group. The rotoreflections of a volleyball. 🏐

Georg Bökman@bokmangeorg.bsky.social · 3mo ago

(Vibe-)Built a visualizer for finite subgroups of O(3). Each point represents a rotation, the direction from the origin is the rotation axis and the distance from the origin the rotation angle. Blue sphere contains pure rotations, red sphere rotations + inversions. georg-bn.github.io/o3-subgroups/

(Vibe-)Built a visualizer for finite subgroups of O(3). Each point represents a rotation, the direction from the origin is the rotation axis and the distance from the origin the rotation angle. Blue sphere contains pure rotations, red sphere rotations + inversions. georg-bn.github.io/o3-subgroups/

Turns out pointmaps are not required after all and you can train rotation prediction via L1 loss on quaternions.

Zhenjun Zhao@ericzzj.bsky.social · 3mo ago

VGGT-Ω @jianyuanwang.bsky.social, Minghao Chen, Shangzhan Zhang, @nikkar.bsky.social, Johannes Schönberger, Patrick Labatut, Piotr Bojanowski, David Novotny, Andrea Vedaldi, Christian Rupprecht arxiv.org/abs/2605.15195

New #Featured Certification: DINOv3 Oriane Siméoni, Huy V. Vo, Maximilian Seitzer et al. https://openreview.net/forum?id=2NlGyqNjns #visual #features #supervised

#illusion le damier qui enfle / bulging checkerboard. Wearing polka dot clothes makes you look larger. Porter des vêtements à pois fait grossir

Accepted to ICML 2026!

Georg Bökman@bokmangeorg.bsky.social · 4mo ago

In our recent preprint, we show in more general settings how identifiability of a network means that equivariance implies layerwise equivariance. arxiv.org/pdf/2601.21645

Accepted to ICML 2026!

Georg Bökman@bokmangeorg.bsky.social · 10mo ago

There's an increasingly popular argument saying that for 3D point clouds with rotational ambiguity (e.g. molecular data) standard transformers are preferable over equivariant models for compute reasons. With “Platonic Transformers” we show why this doesn't have to be true. arxiv.org/abs/2510.03511

Did you know that arXiv has an official merch shop? I didn’t, but I think it’s great. 😅 www.bonfire.com/store/arxiv-...

Support arXiv and open science! | Official Merchandise | Bonfire

an open research sharing platform reinventing scientific communications. Since 1991, scholars have shared their research quickly with their peers before publication on...

bonfire.com

Dear @iclr-conf.bsky.social participants

Marc Lanctot@sharky6000.bsky.social · 3mo ago

Ok, look at the time--- it's April 23rd!!! THE DAY YOU WILL POST ALL YOUR PHOTOS AND VIDEOS OF PAPERS, PRESENTATIONS, AND SOCIALS HAPPENING AT @iclr-conf.bsky.social #iclr #iclr2026 ON BLUESKY! Bring that conference experience to your favorite social network.. we all benefit! 😃🙏

It seems, that we have failed the communication about IMC26. Let's try again. The competition this year is here: kaggle.com/competitions... No prizes, but whole year leaderboard -- similar to KITTY and other academic competitions. 3D people, please retweet and share.

Image Matching Challenge 2025 Ongoing

Ongoing leaderboard for Image Matching Challenge 2025.

kaggle.com

For people using superpoint for image matching, it might be interesting to know that I added a proof-of-concept steerer of superpoint here (making it possible to match rotated images with only one network pass per image): github.com/georg-bn/rot...

We're looking for a new colleague at @amlab.bsky.social: Assistant Professor in AI for Science 🔬🤖 World-class ML research, Amsterdam's thriving AI ecosystem (ELLIS, startups, big tech), and some of the best academic labor conditions in Europe ❤️ Deadline: May 30 👉 werkenbij.uva.nl/en/vacancies...

Vacancy — Assistant Professor in AI for Science (AI4Science)

<p><span>Are you passionate about advancing Machine Learning by integrating insights from the natural sciences? Are you eager to bridge the 3rd (<em><span>computational</span></em>) and 4th (<em><span...

werkenbij.uva.nl

Sparse image matching is done via 1) keypoint detection in each image, 2) keypoint description, 3) matching of descriptions between images. Should rotation invariance be enforced at stage 2 or 3? Turns out both work fine! To be presented at the CVPR image matching workshop by @davnords.bsky.social

Johan Edstedt@parskatt.bsky.social · 4mo ago

Introducing LoMa-R! A rotation invariant version of LoMa. Code: github.com/davnords/loma Paper: arxiv.org/abs/2604.11809

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

Happy Easter! Local Feature Matching has risen! arxiv.org/abs/2604.04931

My university (Chalmers University of Technology in 🇸🇪) is recruiting an assistant professor in data-driven cell & molecular biology, funded by the DDLS program @scilifelab.se #chemsky #facultychemjobs The position comes with a nice start-up package www.chalmers.se/en/about-cha...

Vibe graphing

Georg Bökman@bokmangeorg.bsky.social · 4mo ago

Given the function specifying a sigmoid-MLP f(x)=Wₙσ(⋯σ(W₁x+b₁)⋯)+bₙ, we can recover the weights/biases up to (unique) signed permutations of the neurons by looking at f over the complex numbers, see the quoted thread. What happens if f is odd, i.e. f(x)=−f(−x)?

Given the function specifying a sigmoid-MLP f(x)=Wₙσ(⋯σ(W₁x+b₁)⋯)+bₙ, we can recover the weights/biases up to (unique) signed permutations of the neurons by looking at f over the complex numbers, see the quoted thread. What happens if f is odd, i.e. f(x)=−f(−x)?

Georg Bökman@bokmangeorg.bsky.social · 4mo ago

In 1994 Fefferman proved that by analytically continuing a neural network with sigmoid-activations to the complex numbers, you can read off the weights of the network by looking at the pole structure of the function. www.math.stonybrook.edu/~bishop/clas...

In 1994 Fefferman proved that by analytically continuing a neural network with sigmoid-activations to the complex numbers, you can read off the weights of the network by looking at the pole structure of the function. www.math.stonybrook.edu/~bishop/clas...

arxiv.org/abs/2603.23488 👀 I'll make a detailed thread later

One View Is Enough! Monocular Training for In-the-Wild Novel View Generation

Monocular novel-view synthesis has long required multi-view image pairs for supervision, limiting training data scale and diversity. We argue it is not necessary: one view is enough. We present OVIE, ...

arxiv.org

🔮 Working on ML on curved manifolds? Don't miss out on Jacobi Fields! 🔮 I wrote a quick, highly visual and hopefully accessible introduction to the topic: "Jacobi Fields in Machine Learning" 🤠 Check it out here: olgatticus.github.io/blog/jacobi-...!