Andrei Bursuc

Robotics researchers, this is an occasion not to be missed: top-notch speakers in an excellent location in the Alps this February 🤖⛷️
It's the Winter School on Social Robotics, Artificial Intelligence and Multimedia (SoRAIM), 9-13 Feb 2026 👇

My job in conveying this message became a lot easier as the crowd had been warmed up in the morning with the great discussion between Yann Lecun, Pim de Witte & Aude Durand
Do check it out: x.com/gen_intuitio...

Having reasonably-sized open datasets & models up enables more eyes & brains to look at complex tasks, eg autonomous driving, but not only.
A broader community can debug, break, understand & improve such models in novel ways that a single team working on it might have missed.

Tired Europe: Let's do tons of AI regulations
Wired Europe: Let's do tons of AI open source
#aiPULSE2025

I'm speaking at #aiPULSE2025 today on Open & re-purposable foundation models for the automotive industry.
The morning keynotes talked a lot about open source so my slide here might be timely.

Hey #NeurIPS2025! We have a fun deck of works with the team and friends to present this year. Check them out!

This was a fun project led by @yuanyinnn.bsky.social and awarded as outstanding paper at the NeurIPS #CCFM workshop!

We fermented our thoughts on understanding LoRA & ended up with IPA🍺
We found an asymmetry in LoRA: during training, A changes little & B eats most task-specific adaptation.
So we pre-train A to preserve information before adaptation w/ excellent parameter efficiency #NeurIPS2025 #CCFM 👇

Ah, it’s an insignificant place, at least now when you and @davidpicard.bsky.social are no longer there …

To put this in context: the comment is so great that @chriswolfvision.bsky.social himself went back to X to check it out 😄

Yeah, frankly all potential solutions seem sub-optimal given what a big mess this is.

This seems to have been enacted already: reviewers can't respond or edit their reviews anymore. Authors can still submit comments.

I also think that stopping the process and letting ACs decide based on original reviews would be the safest thing to do at this point to avoid any skewed or suspicion of skewed decisions because of the leak #ICLR2026

Congrats Dr. @nicolasdufour.bsky.social!
So many brilliant works packed in such a short PhD time.

This is by a large margin the most serious problem and mistake in conference peer review I have seen in my career. Apparently a many people were aware of this and many could find out who their reviewers were. This probably has created a large number of unnecessary enmities.

@iclr-conf.bsky.social

Congrats to @loickch.bsky.social & @paulcouairon.bsky.social !
A brilliant duo that brought a fresh deck of ideas this year to significantly improve feature upsampling from JAFAR up to NAF that is now VFM-agnostic 🚀

Check out NAF: an effective ViT feature upsampler to produce excellent (and eye-candy) pixel-level feature maps.

NAF outperform both VFM-specific upsamplers (FeatUp, JAFAR) and VFM-agnostic methods (JBU, AnyUp) over multiple downstream tasks 👇

We have a few fun papers at #BMVC2025
Check them out!

Honored to host a very special guest today: Huy V. Vo, PhD alumnus of @valeoai.bsky.social
He presented his work on automatic data-curation strategies for self-supervised representation learning (DINOv2, DINOv3). Find out more about his research here: huyvvo.github.io

Thrilled to have Jayneel Parekh visiting us over a break in the CVPR sprint to talk about his exciting works in analyzing MLLMs representations. Check out his great work jayneelparekh.github.io

Excellent speaker lineup for the @naverlabseurope.bsky.social AI for Robotics Workshop.
For those at home, the event is live-streamed on the landing page: europe.naverlabs.com/updates/ai4r...

Pro-tip: if you send me an email asking for an internship, a PhD or a postdoc position, don't copy/paste an over-hyped summary of one of my papers you just asked ChatGPT to spit out.

Pro-tip#2: don't do that with other professors as well. It's not just me.

#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.

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.

Post-CVPR deadline run, at last

We've been complaining for years about very short reviews.
Now, we may see a character upper limit to reviews in a near future.

Coarse plan for a 1-week rebuttal period:

day 1: read the reviews
day 2-6: calm down
day 7: write the rebuttal

Unlike ICLR reviews, the sunrise never disappoints

My first smartphone was an iPhone 3GS and then I changed to a series of Android phones in 2013 (HTC One, Lenovo K6, Xiami Note 7, Google Pixel 6) but was always nostalgic about iOS. Now I switched back to an iPhone 16. I waited 2 weeks before writing this, but I am __VERY__ unhappy about iOS.

🧵 1/8

Ah, the most stochastic feature ever: you never know where that Undo button will be each time nor where it will take you once you manage to find it. I still don’t understand the logic.
On the upside, it makes ios so unusable that I ended up using the phone less 😅
A gem of hardware nevertheless …