𝗦𝘂𝗿𝗳𝗹𝗼: 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝘁 𝟯𝗗 𝗦𝘂𝗿𝗳𝗮𝗰𝗲 𝗙𝗹𝗼𝘄 𝗠𝗼𝗱𝗲𝗹 𝘄𝗶𝘁𝗵 𝗚𝗹𝗼𝗯𝗮𝗹 𝗦𝘁𝗮𝘁𝗲 Antoine Guédon, Shu Nakamura, Nicolas Dufour ... Angjoo Kanazawa arxiv.org/abs/2606.13644 Trending on scholar-inbox.com

I'm in the train, and the guy next to me left either for the bathroom or is getting a coffee, and he left his mac open, unlocked. What should I do? When my students do that, I open a text editor and write "I deleted all your latest code and results, have fun!" Tempted to do that...

ACTUALLY, that very same asteroid was already discovered 1990 by the hobby astronomer, Jürgen S.

Very excited to share our new paper, accepted at ICDAR 2026: "Leveraging Morphology for Historical Script Metrological Analysis"! 📜We present a method to automatically extract high-quality character prototypes and compute stable paleographic measurements: malamatenia.github.io/morphology4m...

It's now, wake up! ☕🥐

#CVPR is approaching! If you're interested in human mesh recovery, there is a cool tutorial on Wednesday afternoon. human-mesh-tutorial.github.io (screenshot from the awesome cvprworkshopradar.vercel.app)

🎆 New paper! "Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields", by Julien Lalanne, accepted to ICML'26 🥳 We're proposing flow-matching for inpainting in ultra-sparse setup, with applications to seismic interpolation. 📜 arxiv.org/abs/2605.28625 1/

CVPR@Paris 2026 🇫🇷 — June 1st, co-organised by ELLIS Unit Paris. A one-day local event ahead of CVPR, open to all. Oral & poster sessions for CVPR 2026, CVPR workshops & ICLR 2026 papers. 🔗 https://cvprinparis.github.io/CVPR2026InParis/

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? 🧵

🤔I'm curious and wondering what the global vibe is: what's the best place to do computer vision research at the moment? Happy to read your thoughts on this

🎉 Our work MIRO is accepted to #ICML2026 @icmlconf.bsky.social We integrate human preferences directly during pretraining with multi-reward conditioning. ⚡MIRO is 19x faster than baselines and 370x cheaper at inference! 🤗 Try out the models: huggingface.co/spaces/nicol... See you in Seoul 🇰🇷 !

The model is so fast and easy to use that I vibe-coded a small game with it in 1h 😅 Runs flawlessly on a consumer GPU if you're looking for a small local model to tinker with.

Everything is fully open-sourced, including the codebase, the model + all individual single reward model variants! 🌐 Site: nicolas-dufour.github.io/miro 📄 Paper: arxiv.org/abs/2510.25897 🛠️ Git: github.com/nicolas-dufo... 🤗 HF: huggingface.co/nicolas-dufo... 🎨 Demo: huggingface.co/spaces/nicol...

Thrilled to share that MIRO is accepted to ICML 2026 @icmlconf.bsky.social ! 🎉 By training on the reward scores, we can simply condition the model on high rewards at inference time to guarantee top-tier, aligned outputs. We’ve updated our paper with some additional results!

We are grateful to all of the 17,491 reviewers who helped make #CVPR2026 possible. We are especially pleased to recognize the following Outstanding Reviewers, whose high-quality reviews (as judged by their Area Chairs) placed them among the top 5% of reviewers. 1/2

Playing with some post-processing on a small in-house-but-soon-to-be-released model.

Apparently #CVPR2026 had an outstanding AC initiative. Well done, @davidpicard.eurosky.social!

FAQ on NeurIPS Europe: NeurIPS Europe is an official NeurIPS 2026 satellite event taking place in Paris, France, alongside the main conference in Sydney and the other satellite event in Atlanta. NeurIPS authors can present their papers at any of the three locations, subject to space availability.

So honored and humbled to have won this award! Thanks David ☺️

👏 Folks! If you are curious about the Generative Modeling via Drifting paper, but you find it difficult to understand → I wrote a different interpretation of it. It's called: "An Expectation-Maximization interpretation of Generative Modeling via Drifting" davidpicard.github.io/pdf/An_Expec...

🥳Accepted to ICML, by the way! Old paper here: arxiv.org/abs/2510.25897 (new version up soon) Going to pressure @nicolasdufour.bsky.social to release the code and models! 😅

if you are able to get 14 papers accepted to ICML, maybe you do not actually need to post about getting 14 papers accepted to ICML

Huge congrats @vickykalogeiton.bsky.social for being awarded the médaille de bronze in Computer Science!👏🥳🎉🍾 Very well deserved for all the hard work and fantastic ideas! www.ins2i.cnrs.fr/fr/talents/c... @cnrsinformatics.bsky.social @ipparis.bsky.social @ecolepolytechnique.bsky.social

This very nice paper provides some useful pushback against PRH. To me science is like a damped pendulum, where we need to swing back and forth a few times before converging on truth. So don't worry PRH fans, I'll be trying to swing us back out of the cave again soon!

Excited to share my work as a Student Researcher at Google Zurich: UniGeoCLIP! 🌍🚀 W/ Eduard Trulls, Jan Hosang, @loicland.bsky.social & @pesarlin.bsky.social , we built a framework aligning 5 geospatial modalities in one space. Presented at EarthVision @ #CVPR2026. 🧵👇

I thought I would do a thread, but honestly the post is so good: kyutai.org/blog/2026-04... It explains "One View Is Enough! Monocular Training for In-the-Wild Novel View Generation" arxiv.org/abs/2603.23488 done in colab with the smart people at kyutai

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

🚨 arxiv.org/abs/2604.06129 PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer This paper is the result of doing a lab-wide hackathon on an idea I've had for some time. Probably the paper with the highest number of authors I've ever done. It's a CVPR Findings 26. Thread 🧵👇

👀 arxiv.org/abs/2604.06129 Will do a thread later today

Related read: ergosphere.blog/posts/the-ma...

🚨 Happy to announce CVPR@Paris'26 which will take place on June 1st in Paris. The goal of the event is to share a little bit of the conference before it happens. We will have poster sessions as well as several plenary talks by world-class speakers. info: cvprinparis.github.io/CVPR2026InPa...

Excited to announce our latest (submitted to) SIGBOVIK 2026 @harryqbovik.bsky.social paper: "SchmidhubAI: Accurate Historical Paper Attribution". We built an AI system that, given any modern AI paper, automatically determines which of its ideas were already published by Jürgen Schmidhuber.

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

Today NeurIPS is announcing our official satellite event in Paris. After responding to the call from Ellis following the success of EurIPS in December, we are pleased to reach a new milestone by joining forces with the NeurIPS organizing committee for the 2026 edition.

You will find all official information on the NeurIPS website and on our social networks. NeurIPS Europe is already supported by SSFAM, Hi! Paris, and PRAIRIE-PSL. Satellite General Chairs: Linus Bleistein, Olivier Cappé, Laetitia Chapel, Edwige Cyffers, Rémi Flamary, Pierre Marion

Quick pitstop in Erlangen. Plan to come back later this coming week for a proper visit at FAU hosted, hosted by @visionbernie.bsky.social

I hate the ECCV template so much. Why can't it just die? Nobody prints proceedings into LNCS volumes anymore. My favorite templates: 1. IEEE/CVPR 2. NeurIPS ... ... 39,2312,321. Edging tikz commands in morse code onto the skin of a dead walrus ... ... Springer/ECCV

This year I'm teaching a new course on generative models for visual content (images, video, 3D, etc). It's mostly me rambling about recent papers, design choices I like/hate. The slides of the first lectures are here: davidpicard.github.io/teaching/ Use right arrow to navigate past the blank page.

We have to move all major conferences out of the USA. Nobody wants to get murdered by a militia, ergo no one will attend these conferences. I'm looking at you, CVF...

Get feedback on your #ICML2026 submission from Google's Gemini-based paper assistant tool, an advanced LLM tool specialized to assist with ICML submissions. Live now! More details in the following blog post: blog.icml.cc/2026/01/14/i...

Super accessible write up on what we and others have been up to on representational convergence in AI models, and the platonic representation hypothesis, along with contrary views. I'm a big fan of Quanta Magazine, so it was very cool to see them cover this!

Yesterday, @nicolasdufour.bsky.social defended is PhD. I really enjoyed the years of collaboration w/ @vickykalogeiton.bsky.social (& @loicland.bsky.social) Video: youtube.com/live/DXQ7FZA... Big thanks to the jury @dlarlus.bsky.social @ptrkprz.bsky.social @gtolias.bsky.social A. Efros & T. Karras

Nicolas ( @nicolasdufour.bsky.social ) is defending his PhD right now. I was so in awe of the presentation that I even forgot to take pictures 😅

#KostasThoughts: Please stop using AI tools to write reviews. I want your authentic thoughts, even if they contain spelling, grammar, & factual mistakes. An LLM should not influence your judgment. The purpose of multiple reviewers is to provide diverse views and error checking.

There has to be a decoupling from research for the sake of increasing knowledge, and research for the sake of pleasing VCs. As long as these conference are the key to a career making millions, they will be overflown by people just taking the gamble and thus not taking the reviewing part seriously.

All the slop review drama unfolding at ICLR is painful to watch. But having so many eyes on it puts us in a better point to find solutions. This would have taken longer to be exposed on a closed platform where we may have had a few screenshots and a few author stories at best.

Update on #CVPR2026 full paper & compute form submission issue: We would like to inform authors that the OR submission system requires the submission of a compute reporting form along with any updates to the full paper. We have identified this as a system-related issue. 1/2

This Nature retrospective is quite interesting. To me, the only solution to the credit assignment problem is obvious: stop believing a single person is responsible for every big discovery. It's an artifact of our monkey brain requiring a face for storage, not the reality of how knowledge progresses.

Image generation becomes much more energy efficient. 👍