Profile avatar
bokmangeorg.bsky.social
Geometric deep learning + Computer vision
143 posts 886 followers 361 following
Regular Contributor
Active Commenter
Posts 21 Comments 29

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

submitted 21 hours ago • 3 comments

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.

submitted 3 days ago • 119 comments

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)

submitted 6 days ago • 0 comments

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...

submitted 9 days ago • 0 comments

Excited to share that our paper "Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero" is now out in PNAS! With @nenadtomasev.bsky.social, Tom McGrath, Demis Hassabis, Ulrich Paquet and Been Kim 🎉 📄 doi.org/10.1073/pnas... 🧵(1/8)

submitted 14 days ago • 2 comments

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...

submitted 12 days ago • 1 comment

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...

submitted 13 days ago • 0 comments

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

submitted 14 days ago • 0 comments

#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

submitted 14 days ago • 1 comment

How much 3D do visual foundation models (VFMs) know? Previous work requires 3D data for probing → expensive to collect! #Feat2GS @cvprconference.bsky.social 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis. 🔗Page: fanegg.github.io/Feat2GS

submitted 15 days ago • 1 comment

Can some experienced person please write a guide on how to review borderline papers. Thank you.

submitted 18 days ago • 3 comments

DINO and DINOv2 are surely amazing SSL approaches. Many assume that they're also very simple (in particular vs. other SSL methods), but they are actually a bit more elaborate and I've been in awe of the achievement of the authors. This diagram from SimDINO is more complete.

submitted 19 days ago • 1 comment

Some more Kanatani hot takes :D

submitted 20 days ago • 0 comments

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors Wonbong Jang @weinzaepfelp.bsky.social @vincentleroy.bsky.social Lourdes Agapito Jerome Revaud tl;dr: DUSt3R, but you provide pose,or part of depth or intrinsics. Love the controlability study arxiv.org/abs/2503.17316

submitted 22 days ago • 1 comment

New paper! We merge SfM reconstructions with point cloud registration. Link: arxiv.org/abs/2503.17093 Code: Not yet public, but coming later.

submitted 22 days ago • 9 comments

🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷 Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa... Big 🧵👇 with details!

submitted 26 days ago • 6 comments

It is known that L2-optimal two-view triangulation requires solving a degree 6 polynomial. In the paper below we discuss a reweighting of the cost function that reduces this to a degree 2 polynomial. We also discuss when the cases are equivalent.

submitted 28 days ago • 0 comments

🚀 Paper Release! 🚀 Curious about image retrieval and contrastive learning? We present: 📄 "All You Need to Know About Training Image Retrieval Models" 🔍 The most comprehensive retrieval benchmark—thousands of experiments across 4 datasets, dozens of losses, batch sizes, LRs, data labeling, and more!

submitted 28 days ago • 2 comments

New paper! (arxiv.org/abs/2503.13433), we look into improving the threshold roubustness of Random Sample Consensus (RANSAC) through (less biased) inlier noise scale estimation.

submitted 29 days ago • 4 comments

Here's a graphic on the front page of the New York Times today that has a... uh... expansive definition of AI. The good news is, by this definition, every computer since the PDP-6 introduced multitasking in 1964 now counts as A.I. computing.

submitted 29 days ago • 0 comments

Some hard evals. 1) IMC24 train -- Lizard. Reconstruction is good, but summer and winter are two separate nearby 2) IMC 24 train -- pond. Results are hard to tell. 3) Room with mirror - almost ideal Overall the results are very impressive, but SfM is not solved yet. 1/

submitted 29 days ago • 1 comment