iiinova — where your digital self keeps evolving

Reposted by valeo.ai

ELLIOT Project @elliot-eu.bsky.social · 22/09/2026

We were in Barcelona for the Summer School on Autonomous Driving! 🚗 The event explored how AI can support safer, smarter mobility in complex real-world environments. It was great to see so much curiosity, technical exchange and energy in Barcelona. 🤝

042

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 16/09/2026

We start the 2nd #ssad2026 day with @kashyap7x.bsky.social talking about: Making progress measurable - Evaluation and benchmarking of driving policies

1124

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 16/09/2026

Fatma Güney up next speaking on Learning compact state representations for reliable autonomous driving #ssad2026

181

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 16/09/2026

The Carla OG German Ros talks about Synthetic data workflows to accelerate AV #ssad2026

151

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 15/09/2026

José M. Alvarez speaks of End-to-end models for autonomous driving - from direct prediction to counterfactual deliberation on the edge #ssad2026

161

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 15/09/2026

Maximilian Igl on stage talking about Reinforcement Learning for Autonomous Driving #ssad2026 His slides are available online www.maximilianigl.com/blog/rl-for-...

191

Reposted by valeo.ai

Tetiana Martyniuk🇺🇦@ ICIP’26🇫🇮 @t-martyniuk.bsky.social · 16/09/2026

(1/n) Can older lidar SSC models catch up with recent SOTA just by getting better inputs? At #ICIP2026 today and in our new journal extension, we add two cheap priors to existing networks, with no redesign. 📍 Poster #2752, Park Hall, 14:00–16:00 🇫🇮 🧵👇

182

valeo.ai @valeoai.bsky.social · 07/09/2026

Can a car learn to drive by playing against itself, using only its cameras? Self-play driving agents have relied on a shortcut: perfect knowledge of every vehicle's position and speed, even the ones they can't see. A real car never gets that. We take the shortcut away. 🧵

1154

valeo.ai @valeoai.bsky.social · 07/09/2026

We’ll be @eccv.bsky.social to present our most recent research! We’ll present three papers in the main conference & two in the Workshops. We will also speak in two workshops & one tutorial. Here is a quick overview on the works we’ll resent in Malmö #eccv2026 valeoai.github.io/posts/eccv-2...

162

valeo.ai @valeoai.bsky.social · 27/07/2026

Multiple #ECCV2026 outstanding reviewer awards at @valeoai.bsky.social! Congrats to A. Boulch, @abursuc.bsky.social, @anhquancao.bsky.social, N. Samet, @t-martyniuk.bsky.social, Y. Xu, to our visiting PhD student E. Karypidis, and to our alumnus @gillespuy.bsky.social!

0102

Reposted by valeo.ai

ELLIOT Project @elliot-eu.bsky.social · 23/07/2026

How can AI better understand 3D driving scenes? 🚗 In this ELLIOT Research Spotlight 🔬, we highlight LOSC from @valeoai.bsky.social: a method for open-vocabulary LiDAR segmentation that helps assign meaning to 3D point clouds, beyond fixed object categories. Paper + code in comments 👇

122

valeo.ai @valeoai.bsky.social · 06/07/2026

New state of the art in one-step image generation 🏆 One forward pass. The method is so simple it's almost unsettling: no teacher, no discriminator, no denoising trajectory 🧵

151

valeo.ai @valeoai.bsky.social · 03/07/2026

valeo.ai is heading to #ICML2026 and #ACL2026 with two papers: - diverse LLM decoding with LoRA-MCL, - counterfactual explanations for driving LLMs with DRIV-EX 🧵👇

131

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 19/06/2026

The #WorldEngine tech report is now up! It's our post-training framework to deal w/ scarcity of long-tail safety-critical scenarios. Post-training strategies for autonomous driving are rarely tackled and discussed in the open. We hope that this will open more this area. arxiv.org/abs/2606.19836

1132

valeo.ai @valeoai.bsky.social · 03/06/2026

Great event at CVPR in Paris! 🎉 The @valeoai.bsky.social team got to present several posters and had a lot of fun discussions with the community. Thanks to everyone who stopped by!

161

valeo.ai @valeoai.bsky.social · 02/06/2026

The team valeo.ai is at #ICRA2026 in Vienna! 2 papers: one on LiDAR scene generation w/ RGB-pretrained priors, and one on pretraining motion forecasting models from pseudo-labeled trajectories.

110

Reposted by valeo.ai

ELLIOT Project @elliot-eu.bsky.social · 01/06/2026

The schedule for the ELLIS Summer School on Autonomous Driving (SSAD 2026) is LIVE! 🏎️✨ 4 days of top-tier AI & robotics research in Barcelona, proudly supported by ELLIOT. ⏳ 7 days left to apply! Secure your spot: 🔗 pages.cvc.uab.es/ssadriving/ @ellis.eu @valeoai.bsky.social @uab.cat

072

valeo.ai @valeoai.bsky.social · 01/06/2026

Our recent research will be presented at #CVPR2026 @cvprconference.bsky.social! We’ll present nine papers in the main conference and we’ll be speaking in two workshops & one tutorial Here is a quick overview on the works we’ll be presenting in Denver: valeoai.github.io/posts/cvpr-2...

1134

valeo.ai @valeoai.bsky.social · 28/05/2026

Amaia Cardiel gave an invited talk at the "Explainable AI" Day of the CNRS Normastic research federation (GREYC Caen / LITIS Rouen), on "Explaining autonomous driving systems: from driving classifiers to driving LLMs"

060

valeo.ai @valeoai.bsky.social · 18/05/2026

Multiple CVPR 2026 outstanding reviewer awards at @valeoai.bsky.social! Congrats to @anhquancao.bsky.social, D. Hurych, N. Samet, @t-martyniuk.bsky.social, Y. Xu, and alumni @gillespuy.bsky.social, S. Venkataramanan, F. Bartoccioni, @bjoernmichele.bsky.social. media.eventhosts.cc/Conferences/...

media.eventhosts.cc

092

Reposted by valeo.ai

ELLIOT Project @elliot-eu.bsky.social · 18/05/2026

The future of Autonomous Driving is heading to Barcelona! 🏎️🏙️ Supported by ELLIOT, this ELLIS Summer School allows researchers to learn from experts and build new collaborations over four intensive days. 🚀 Apply by 8 June! ⏳ pages.cvc.uab.es/ssadriving/ @ellis.eu @valeoai.bsky.social @uab.cat

051

Reposted by valeo.ai

Evangelos Kazakos @ekazakos.bsky.social · 02/05/2026

go.bsky.app/AJubGZF I made this starter pack with ML/AI companies on Bluesky. For now it's a bit short, but we hope to see it growing as more companies land on here. If you are interested, please follow them to encourage them staying on Bluesky. If I missed any, pls let me know to add them!

44310

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 29/04/2026

We have a stellar line-up of confirmed speakers with us: @alexandreboulch.bsky.social, @kashyap7x.bsky.social, @fguney.bsky.social, @maxigl.bsky.social, José M. Álvarez, Antonio M. López, Holger Caesar, German Ros, Vassia Simaiaki and more to come!

182

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 29/04/2026

📣 ELLIS | ELLIOT Summer School on Autonomous Driving 🚗 Super happy to announce the hottest event this summer. Apply now! 📅 September 15-18, 2026 📍Barcelona, Spain 🌐 pages.cvc.uab.es/ssadriving/ @ellis.eu, ELLIS-Barcelona, CVC-Barcelona, @valeoai.bsky.social ai.bsky.social, @elliot-eu.bsky.social

2216

valeo.ai @valeoai.bsky.social · 21/04/2026

This week, at #ICLR2026, we are presenting: RAP: 3D Rasterization Augmented End-to-End Planning 👉 Project page w/ code: alan-lanfeng.github.io/RAP/ Collab with VITA lab from EPFL @iclr-conf.bsky.social #Bench2Drive #navsim

062

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 20/04/2026

🌍WorldEngine is one of the most exciting projects in AD in the past years! It's a post-training framework tackling the scarcity of long-tail safety-critical scenarios by: mining -> 3DGS reconstruction and dynamic agents control w/ behavior world models -> RL post-training. Blog, code and data are up

092

valeo.ai @valeoai.bsky.social · 20/04/2026

Our visiting PhD student @bliberatori.bsky.social gave us a great talk on Video understanding beyond trimmed clips: temporal and comparative reasoning. Make sure to have a look at her excellent works in this area: benedettaliberatori.github.io

150

Reposted by valeo.ai

Sophia Sirko-Galouchenko 🇺🇦 @ssirko.bsky.social · 17/04/2026

1/n New paper - V-GIFT 🎁 Self-supervised tasks like rotation prediction or colorization were big in 2018. Do they still matter? Yes. We turn them into visual instruction tuning data for MLLMs. Result: models rely more on the image and perform better on vision tasks 👀

1238

Reposted by valeo.ai

The EXA4MIND Project @exa4mind.bsky.social · 14/04/2026

👋 Farewell to EXA4MIND | David Hurych from @valeoai.bsky.social and the industrial application case leader of EXA4MIND. As EXA4MIND draws to a close, we have brought together consortium members to discuss the project's impact over the last three years. ⬇️ www.youtube.com/watch?v=mV-Y...

youtube.com

EXA4MIND farewell | David Hurych, industrial application case leader (VALEO)

YouTube video by EXA4MIND

011

valeo.ai @valeoai.bsky.social · 16/04/2026

Congrats to our team member Marc Lafon for being awarded the 2026 AFRIF PhD prize! 🎉 afrif.irisa.fr?page_id=54

070

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 27/03/2026

Congrats Dr. @vletzelter.bsky.social for his work defended in front of a stellar jury and answering to so many questions that @rflamary.bsky.social decided a break at some point ^^ Fun fact: Victor had not 4, not 6, but *8* advisors over the span of his thesis and he handled them brilliantly

181

valeo.ai @valeoai.bsky.social · 27/03/2026

Congrats to our @vletzelter.bsky.social for earning his PhD for his work on "Multiple Choice Learning from Ambiguous Signals". Victor is a resourceful, curious and kind researcher. Good luck for next! Fruit of an excellent collaboration between @telecomparis.bsky.social & @valeoai.bsky.social

051

Reposted by valeo.ai

Rémi Flamary @rflamary.bsky.social · 24/03/2026

I'm totally biased on this but I think it's wonderful that we now have official NeurIPS parallel satellite events. Parallelization was the trick that allowed us to scale to large data and models. It makes sense to try it for conferences as the community grows.

2277

valeo.ai @valeoai.bsky.social · 24/03/2026

🚨 Happening NOW! 🎓 Our PhD student Victor Letzelter @vletzelter.bsky.social is currently defending his thesis at Telecom Paris! Good luck, Victor! 👏🚀 #PhDDefense #TelecomParis

020

valeo.ai @valeoai.bsky.social · 20/03/2026

3DV starts TODAY! The valeo.ai team is thrilled to be there to present our latest research focusing on advancing LiDAR segmentation #3DV #3DV2026 #3D #LiDAR Check out the below for details! 👇

140

valeo.ai @valeoai.bsky.social · 19/03/2026

Congratulations to our researchers Renaud Marlet and @abursuc.bsky.social on their repeated recognition as outstanding reviewers at #CVPR, #ICCV, and #ECCV👏👏👏 Thank you for your sharp insights, kindness, and dedication. It's key for the field to count on reviewers like you!

1154

Reposted by valeo.ai

ELLIOT Project @elliot-eu.bsky.social · 12/03/2026

ELLIOT partners came together in Modena. 🤝 With 34 partners across 13 countries, the consortium met this week to review progress, discuss challenges and align on next steps, strengthening collaboration across Europe. 🌍

251

valeo.ai @valeoai.bsky.social · 06/03/2026

CLIP's visual embedding projector is a few-shot cornucopia 💡Few-shot adaptation of VLMs by fine-tuning the last matrix of the vision encoder 📜https://arxiv.org/abs/2410.05270 💻code available ✅ by M. Fahes, @tuanhungvu.bsky.social, @abursuc.bsky.social, @ptrkprz.bsky.social, R. de Charette

041

valeo.ai @valeoai.bsky.social · 23/02/2026

Tune in to the live PhD defense of Loïck Chambon on "Efficient Representations for Autonomous Driving", a PhD co-advised by @mlia-isir.bsky.social & @valeoai.bsky.social www.youtube.com/live/uFMAHn0...

youtube.com

PhD defense - Loïck CHAMBON

YouTube video by mlia deeplearning

062

valeo.ai @valeoai.bsky.social · 20/02/2026

Energized and inspired after our annual meetup to brainstorm on new exciting ideas and plan the projects ahead of us this year! As always this is an excellent occasion to fit (almost) the entire team in a single photo

0111

Reposted by valeo.ai

TMLR Published Papers @tmlr-pub.bsky.social · 03/02/2026

IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adap... Yuan Yin, Shashanka Venkataramanan, Tuan-Hung Vu, Andrei Bursuc, Matthieu Cord Action editor: Ofir Lindenbaum openreview.net/forum?id=aLmQeZx2pR #projector #adaptation

052

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 09/01/2026

The unreasonable magic of simplicity! Meet DrivoR (Driving on Registers): our latest end2end autonomous driving model. We teared down complex dependencies & modules from current models to obtain a pure Transformer-based SOTA driving agent (NAVSIM v1 & v2, HUGSIM). Find out more 👇

041

valeo.ai @valeoai.bsky.social · 09/01/2026

1/🧵 Q: Can we have both a simple and SOTA architecture in autonomous driving? R: Yes! 😍 Introducing Driving on Registers (DrivoR): a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation. Here is how 👇

1104

valeo.ai @valeoai.bsky.social · 10/12/2025

Our @spyrosgidaris.bsky.social is speaking this morning (Wed, Dec 10th, 11:00 am Paris time) about "Latent Representations for Better Generative Image Modeling" in the Hi! PARIS - ELLIS monthly seminar. The talk will be live-streamed: www.hi-paris.fr/2025/09/26/a...

hi-paris.fr

AI Seminar Cycle – Hi! PARIS

072

valeo.ai @valeoai.bsky.social · 04/12/2025

Perfect timing for this keynote on open, re-purposable foundation models at #aiPULSE2025 @abursuc.bsky.social taking the stage this afternoon! 👇

020

valeo.ai @valeoai.bsky.social · 03/12/2025

Check out our works at @NeurIPSConf #NeurIPS2025 this week! We present 5 full papers + 1 workshop about: 💡 self-supervised & representation learning 🖼️ generative image models 🧠 finetuning and understanding LLMs & multimodal LLMs 🔎 feature upsampling valeoai.github.io/posts/neurip...

151

Reposted by valeo.ai

Andrei Bursuc @abursuc.bsky.social · 02/12/2025

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 👇

171

Reposted by valeo.ai

Yuan Yin @yuanyinnn.bsky.social · 02/12/2025

1/Serve your PEFT with a fresh IPA!🍺 Finetuning large models is cheaper thanks to LoRA, but is its random init optimal?🤔 Meet IPA: a feature-aware alternative to random projections #NeurIPS2025 WS #CCFM Oral+Best Paper Work w/ S. Venkataramanan @tuanhungvu.bsky.social @abursuc.bsky.social M. Cord 🧵

1122

Reposted by valeo.ai

Mickael Chen @mickaelchen.bsky.social · 26/11/2025

That was a cool project brillantly led by Ellington Kirby during his internship. We were curious if we could train diffusion models on sets of point coordinates. For images, this is a step towards spatial diffusion, with pixels reorganizing themselves, instead of diffusing in rgb values space only.

032