Tracking the spookiest runs @weightsbiases.bsky.social

The worst part about leaving academia is that you loose eduroam access :(

lol, a #WACV AC just poorly rephrased the weaknesses I raised in my review as their justification and ignored all other reviews ... I feel bad for the authors ...

🚨 New paper out! "VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes" 👉 arxiv.org/abs/2509.25339 We test 37 VLMs on 2,700+ VQA questions about dense scenes. Findings: even top models fumble badly—<20% on the hardest split and key failure modes in counting, OCR & consistency.

Is basic image understanding solved in today’s SOTA VLMs? Not quite. We present VisualOverload, a VQA benchmark testing simple vision skills (like counting & OCR) in dense scenes. Even the best model (o3) only scores 19.8% on our hardest split.

Congratulations to @paulgavrikov.bsky.social for an excellent PhD defense today!

Yesterday, I had the great honor of delivering a talk on feature biases in vision models at the VAL Lab at the Indian Institute of Science (IISc). I covered our ICLR 2025 paper and a few older works in the same realm. youtu.be/9efpCs1ltcM

What an incredible week at #ICLR 2025! 🌟 I had an amazing time presenting our poster "Can We Talk Models Into Seeing the World Differently?" with @jovitalukasik.bsky.social. Huge thanks to everyone who stopped by — your questions, insights, and conversations made it such a rewarding experience.

Today at 3pm - poster #328. See you there!

On Thursday, I'll be presenting our paper "Can We Talk Models Into Seeing the World Differently?" (#328) at ICLR 2025 in Singapore! If you're attending or just around Singapore, l'd love to connect—feel free to reach out! Also, I’m exploring postdoc or industry opportunities–happy to chat!

We should start boycotting proceedings that do not have a "cite this article" button.

Proud to announce that our paper "Can We Talk Models Into Seeing the World Differently?" was accepted at #ICLR2025 🇸🇬. This marks my last PhD paper, and we are honored that all 4 reviewers recommended acceptance, placing us in the top 6% of all submissions.

I analyzed the top 20 most common words in titles of all computer vision (cs.CV) papers on arxiv since 2007. A lot of "learning" papers ...

10 years ago #ICLR (2014) only had 69 submissions, today nearly 12k. So many good papers: openreview.net/group?id=ICL...

Yeah, I am sure my paper on Feature Biases in ImageNet classifiers is a great match for a journal on lifestyle and sustainable goals.

Today at #NeurIPS2024 Interpretable AI Workshop! Poster sessions are at 10am and 4pm. "How Do Training Methods Influence the Utilization of Vision Models?" arxiv.org/abs/2410.14470 We won’t be there, but Ruta Binkyte is presenting for us!

Gemini 2.0 Flash is the best free-to-use LLM for writing tasks, blazing fast, and last-but-not-least available in the EU ...

One of the most interesting aspects of adversarial training to me is not that it increases robustness, but it's ability to revert biases. If a model is strongly biased for X, it will likely completely ignore X at sufficient eps. This is clearly visible in the texture/shape bias!

The adaption of ChatGPT amongst non-tech users is incredible - I see so many people in public transport using the app.

Tired of showing the same old same adversarial attack examples? Generate your own with this little Foolbox-based Colab: colab.research.google.com/drive/1WfqEW...

WILD! Some researchers from have republished ResNet under their own names at some predatory journal. @csprofkgd.bsky.social Predatory: ijircce.com/admin/main/s...

#ICLR best rebuttal award goes to ...