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

I recently had to switch to an iphone after an entire life on android phones. First shock is how bad and limited is the ios clock app compared to the google one -- I might be using alarms in very peculiar ways 😅 If you're out of ideas you can always have a look on what other folks are trying out.

We introduce MIRO: a new paradigm for T2I model alignment integrating reward conditioning into pretraining, eliminating the need for separate fine-tuning/RL stages. This single-stage approach offers unprecedented efficiency and control. - 19x faster convergence ⚡ - 370x less FLOPS than FLUX-dev 📉

The perks of early risers

Launching the Physical AI AV Dataset! 🚀 huggingface.co/datasets/nvi... One of the largest, most diverse & commercially usable open-source datasets for AVs. - 1727 hours of driving data - Camera, LiDAR, & radar - 25 countries, 2500+ cities This is just the beginning, more features to come!

This is a major reset for autonomous driving research! So exciting 🚀

X-mas came earlier this year! Nvidia has just released the huge Physical AI AV Dataset - 1727 hrs of driving data: 310K clips of 20s - sensor rig: 7 cameras, lidar, radar - 25 countries, 2.5K cities from US + Europe Kudos to @kashyap7x.bsky.social et al.! huggingface.co/datasets/nvi...

EuroHPC wrote a piece about our love of GPUs 😊 A EuroHPC Success Story | Clear Vision for Self-Driving Cars www.eurohpc-ju.europa.eu/eurohpc-succ...

A reminder which might be relevant now: we are looking to hire a senior research scientist in Robotics at @naverlabseurope.bsky.social in Grenoble, France.

Happy to represent Ukraine at #ICCV2025 . Come see my poster today at 11:45 (#399)!

Today is the day for our @iccv.bsky.social workshop that we've been cooking with excitement in the past months. Learning to See: Advancing Spatial Understanding for Embodied Intelligence #ICCV2025 Join us! opendrivelab.com/iccv2025/wor...

Trying to mitigate ICCV FOMO today. Staying at home this time. Have fun everybody!

Our recent research will be presented at @iccv.bsky.social! #ICCV2025 We’ll present 5 papers about: 💡 self-supervised & representation learning 🌍 3D occupancy & multi-sensor perception 🧩 open-vocabulary segmentation 🧠 multimodal LLMs & explainability valeoai.github.io/posts/iccv-2...

Belle lune

Hear! Hear!

“Has anyone heard about DUSt3R?” All hands and hearts up in the room. Honored to welcome @gabrielacsurka.bsky.social today to speak about the amazing work @naverlabseurope.bsky.social towards 3D Foundation Models

The unreasonable effectiveness of mastering the skill of placing <EOS> in real life

The outstanding reviewer award is definitely one of my favorite type of awards as good reviewing helps so much to advance our community and research forward. Congrats to all great reviewers out there whether rewarded this time or not! #iccv2025

Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏 Andrei Bursuc @abursuc.bsky.social Anh-Quan Cao @anhquancao.bsky.social Renaud Marlet Eloi Zablocki @eloizablocki.bsky.social @iccv.bsky.social iccv.thecvf.com/Conferences/...

Some night runs seem more like sightseeing than running

Here we go again 😅 This time I’m planning to take a more senior role to help mentor the next gen of publicity chairs. Please consider volunteering!

Many treat uncertainty = a number. At Apple, we're rethinking this: LLMs should output strings that reveal all information of their internal distributions. We find that Reasoning, SFT, CoT can't do it - yet. To get there, we introduce the SelfReflect benchmark. arxiv.org/pdf/2505.20295

Update: ResearchGate has investigated the case, and, as far as I can see, all the suspicious papers (~200) have now been removed. Many thanks to the @researchgate.bsky.social team!

CoRL 2025 is just around the corner in Seoul, Korea! 🤖 🚗 We're excited to present our latest research and connect with the community. #CoRL2025

In my brain every time I connect to overleaf during deadline periods, I see this

A new season in full swing with a winning duo: kids do hockey, dad does overleaf

The French often mention the roundabout at Arc de Triomphe as one of the ultimate tests for a self-driving vehicle. I would say that the equivalent for humanoid robots would be to unwrap Chupa Chups Lollipop. Take that Embodied AI!

No time to shed tears post-NeurIPS when ICLR deadline is so close ...

Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway. We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff! 📝 arxiv.org/abs/2412.06014

Our NeurIPS submission arxiv.org/abs/2502.08938 did not get in, but it's one of my favorite papers and I think one of the better papers we've ever put out so I want to highlight it

In the last weeks we noticed that our RangeViT was getting increasingly numerous citations from unrelated papers uploaded to ResearchGate and other platforms. Check out the investigation of @gillespuy.bsky.social on this issue that may impact other papers too.

If you're interested in human pose estimation and mesh recovery from LiDAR data, we have this massive survey: arxiv.org/abs/2509.12197 Salma and Nermin put a tremendous amount of work in it, there's everything: the tasks, all the methods organized, datasets, numbers, challenges and opportunities.

Quite a hefty video dataset just released: 7K hours of video with various annotations: camera pose, depth maps, dynamic object masks, scene text descriptions (camera, motion trends, summary) SpatialVID: A Large-Scale Video Dataset with Spatial Annotations nju-3dv.github.io/projects/Spa...

Not your average "join us" type of video: Je suis Elodie. A touching mini-documentary following Elodie, a researcher at Owkin on cancer treatment and fighting with her own breast cancer www.docplus.com/details/je-s...

The Colloquium in Pattern Recognition and Computer Vision of the Visual Recognition Group at CTU in Prague has a long tradition dating back to 1998. The list of all speakers is available docs.google.com/spreadsheets.... Enjoy! The 50th edition is coming soon cmp.felk.cvut.cz/colloquium/

Announcing the @iccv.bsky.social NAVSIM Challenge! What's new? We're testing not only on real recordings, but also perturbed futures generated from the real ones via pseudo-simulation! $8K in prizes + several $1.5k travel grants. Submit by September 20! opendrivelab.com/challenge2025/ 🧵👇

This! The way I explain RL to beginners (I sometimes hear stuff like "it's just supervision but given a fancy name"): Me: "Imagine you don't know how to solve a task, but you know how to evaluate if it is well done when its done. That's the objective of RL, you optimize your metric*." 1/3

Hi friends! I made a computer vision feed that was missing on Bluesky. You can find it here: bsky.app/profile/did:.... Pin it to your profile if you like it. 😉 It filters relevant posts based on regular expressions. But to make sure that your post is included in the feed, add the #skyvision tag.

Slurm for scheduling busy families with kids on weekends: parents submit their jobs/chores/activities requests (individual or collective) and they are queued based on priority, duration, calendars, karma, etc.

Slurm for scheduling busy families with kids on weekends: parents submit their jobs/chores/activities requests (individual or collective) and they are queued based on priority, duration, calendars, karma, etc.

Next week, I'll be in Strasbourg for the GRETSI (@gretsi-info.bsky.social) to present a small discovery on transformers generalization we made with Simon and Jérémie while working on generative recommender systems. I love these "phase transition" plots. 📜: arxiv.org/abs/2508.03934 Short summary 👇

Very effective trick! Now, does anyone have a trick to quickly memorize those cryptic hashes we use for reviewer IDs on OpenReview? My brain got messed up again after this round of NeurIPS meta-reviewing 🥲

AI efficiency is important. The median Gemini Apps text prompt in May 2025 used 0.24 Wh of energy (<9 seconds of TV watching) & 0.26 mL (~5 drops) of water. Over 12 months, we reduced the energy footprint of a median text prompt 33x, while improving quality: cloud.google.com/blog/product...

To clarify, my intention is not to smash CLIPs (really loving them actually), but to bring up merits that are overlooked in discussions. I'm using both types of models where they are strong at.

On the CLIP vs. SSL image encoder debate: an overlooked aspect is how much fewer GPU resources SSL models need compared to CLIP ones for pretraining. Recent examples: - SSL: Franca - 128 H100, bsz 3K; DINOv3 - 256 H100, bsz 4K - CLIP: SigLIP2 - 2048 TPUv5, bsz 32K; PE - bsz 131K

Look what I got in my mail today: the new book @thomwolf.bsky.social The ultra-scale playbook: Training LLMs on large GPU clusters 🚀

Have you ever asked yourself how much your favorite vision model knows about image capture parameters (e.g., the amount of JPEG compression, the camera model, etc.)? Furthermore, could these parameters influence its semantic recognition abilities?

None of our impactful papers have had an easy path through traditional venues. Most cited paper? Rejected four times. Most impactful paper? Poster at a conference. But none of it matters because arxiv makes everything work