Sign in

Andrei Bursuc

@abursuc.bsky.social
5.3K followers 381 following 704 posts

Research Scientist at valeo.ai | Teaching at Polytechnique, ENS | Alumni at Mines Paris, Inria, ENS | AI for Autonomous Driving, Computer Vision, Machine Learning | Robotics amateur ⚲ Paris, France 🔗 abursuc.github.io

PostsRepliesMedia
Andrei Bursuc @abursuc.bsky.social · 26/09/2026
Kids and dad sprinting side by side in their own way. Let’s go ICLR!
181
Reposted by Andrei Bursuc
Christian Wolf @chriswolfvision.bsky.social · 24/09/2026
We had X NeurIPS 2026 submissions and Y of them passed, X-Y were rejected. The actual counts are irrelevant, as every Y was appreciated and each and every X-Y hurt. These were the last ones where coding was done 100% by humans 💪. Also writing btw, but we continue to do all our writing ourselves.
1134
Andrei Bursuc @abursuc.bsky.social · 22/09/2026
It looks like a terrific day for Slovenian domain name sellers 🙃
140
Reposted by Andrei Bursuc
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
Andrei Bursuc @abursuc.bsky.social · 19/09/2026
🚗 SSAD 2026 is done! Great talks, two packed poster sessions, and an incredible audience that kept asking questions well after the session should have ended. Thank you to our speakers, our sponsors, and the 72 people who made it what it was. We had a blast! #ssad2026
130
Andrei Bursuc @abursuc.bsky.social · 19/09/2026
Closing remarks of #ssad2026 by @pdillis.bsky.social
020
Andrei Bursuc @abursuc.bsky.social · 18/09/2026
Last talk of #ssad2026: Dirk Hornung on OpenXLA: ready to use end-to-end compiler stack #ssad2026
040
Andrei Bursuc @abursuc.bsky.social · 18/09/2026
The one and only Holger Caesar on stage with Autonomous Driving at the crossroads: scaling laws, end to end learning, and the gap between #ssad2026
140
Andrei Bursuc @abursuc.bsky.social · 18/09/2026
Antonio Lopez starts day 4 #ssad2026 with Vision-based end-to-end driving: CVC experience.
150
Andrei Bursuc @abursuc.bsky.social · 17/09/2026
Puneet Dokania on stage speaking about VLAs for drivong: why, how, and challenges? #ssad2026
120
Andrei Bursuc @abursuc.bsky.social · 17/09/2026
Kicking off day 3 of #ssad2026 with Sofía Dudas talking about World Models for Autonomous Driving
290
Andrei Bursuc @abursuc.bsky.social · 16/09/2026
Fireside chat with today’s speakers: @kashyap7x.bsky.social, German Ros, Fatma Güney, hosted by Gabriel Villalonga #ssad2026
090
Andrei Bursuc @abursuc.bsky.social · 16/09/2026
The Carla OG German Ros talks about Synthetic data workflows to accelerate AV #ssad2026
151
Andrei Bursuc @abursuc.bsky.social · 16/09/2026
Fatma Güney up next speaking on Learning compact state representations for reliable autonomous driving #ssad2026
181
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
1123
Reposted by Andrei Bursuc
David Picard @davidpicard.eurosky.social · 14/09/2026
New year, new semester, new course, new textbook: davidpicard.github.io/mldl/mldl-bo... 👀 Still in draft form, but not in a bad shape.
davidpicard.github.io
23511
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
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
Andrei Bursuc @abursuc.bsky.social · 15/09/2026
First session of the day by Alexandre Boulch on 3D perception in autonomous driving: from Lidar self-supervision to multi-sensor distillation #ssad2026
030
Andrei Bursuc @abursuc.bsky.social · 15/09/2026
Let’s go #ssad2026
030
Andrei Bursuc @abursuc.bsky.social · 15/09/2026
Kicking off the ELLIS Summer School on Autonomous Driving today. What an amazing venue #ssad2026
091
Reposted by Andrei Bursuc
Diane Larlus @dlarlus.bsky.social · 08/09/2026
@noagarciad.bsky.social speaking at the #ECCV2026 workshop on uncertainty, being introduced by @abursuc.bsky.social
3102
Reposted by Andrei Bursuc
Noa Garcia @noagarciad.bsky.social · 08/09/2026
I'm talking today at the Uncertainty Quantification for Computer Vision workshop. 15:30 @ Quality View Hotel, Helsingborg room
032
Reposted by Andrei Bursuc
Giorgos Tolias @gtolias.bsky.social · 06/09/2026
Choices in the image acquisition and processing pipeline leave traces in the representation space of foundational vision encoders. At ECCV 2026 we discuss about the what, the why, and the how to fix it. @eccv.bsky.social #ECCV2026
1165
Reposted by Andrei Bursuc
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
Reposted by Andrei Bursuc
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
Andrei Bursuc @abursuc.bsky.social · 07/09/2026
Super proud of Pictura: our GPU-accelerated multi-agent driving simulator that renders super-fastly the ego-centric view of every agent at every time step. This enables us now to train driving policies with self-play at scale without privileged information. Find out more below 👇
070
Reposted by Andrei Bursuc
Pier @pierl.bsky.social · 06/09/2026
Most of what @thegoodailab.bsky.social does can be described as building a connection. A bridge between frontier AI research and humanitarian action, education, and sustainability. 🌱🧵 cv4good.thegoodailab.org w/@msf.org
cv4good.thegoodailab.org
CV4GOOD — Computer Vision for Humanitarian Action
ECCV 2026 workshop in Malmö, Sweden on Tuesday, September 8, 2026, pairing CV researchers with humanitarian practitioners from MSF.
1106
Andrei Bursuc @abursuc.bsky.social · 06/09/2026
🛟 Reliable & reliability folks @eccv.bsky.social! Join our workshop on Uncertainty Quantification for Computer Vision #eccv2026 We have a super lineup of speakers (from computer vision to MLLMs & LLMs) and cool posters. 🗓️ Date: Tue Sep 8 📌Room: Quality View Hotel - Helsingborg
1137
Reposted by Andrei Bursuc
Mert Bulent Sariyildiz @mbsariyildiz.bsky.social · 01/09/2026
🧐 Can you distill knowledge from 4 vision teachers into one student using ZERO real images? 🥳 Turns out: YES, and surprisingly well. 📣 Our ECCV 2026 paper "IDeaL" closes most of the gap with real-image distillation, using optimized structured noise.
1279
Andrei Bursuc @abursuc.bsky.social · 17/08/2026
All booked for #ECCV2026 I’ll be there for the workshops and tutorials. Really looking forward to catching up with folks, papers, posters, and talks. See you in Malmö!
0130
Reposted by Andrei Bursuc
Transactions on Machine Learning Research @tmlrorg.bsky.social · 13/08/2026
Starting September 1, 2026, TMLR will no longer be considering survey papers for review. This is in part due to limited reviewer resources and significant required labour for reviewing surveys, as well as the evolving role of surveys in our field.
0126
Reposted by Andrei Bursuc
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 12/08/2026
For the past six months @mariaa.bsky.social and I have been working on creating an improved research experience on atproto. It's now live! Check out: lea.ac
leaflet.pub
Lea: research-oriented social media
Introducing a beta-version of our new research-focused social media platform
20381113
Reposted by Andrei Bursuc
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 11/08/2026
Thinking on "high integrity" research, we push students to do slow science, to be upfront about limitations, to balance learning with exploiting. While obviously moral, it must also be the case that by doing this students eventually "win", else you're just creating a generation where... 1/2
2444
Reposted by Andrei Bursuc
Naomi Saphra @nsaphra.bsky.social · 09/08/2026
I've been unsettled lately when reading messages and papers. It feels like I'm dissociating. Everything seems a bit alien, even if it's completely human. I've had a realization: When our simulations finally exited the Uncanny Valley, they brought the Uncanny with them.
nsaphra.net
Life on the Uncanny Precipice | Naomi Saphra
We were wrong about the Uncanny Valley.
1026362
Reposted by Andrei Bursuc
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 06/08/2026
With the new year upcoming, spent some time putting together an AI usage policy to think through how it's used in research and learning: three-sundial-55c.notion.site/AI-Usage-Pol...
three-sundial-55c.notion.site
AI Usage Policy | Notion
TLDR: this is a continually evolving doc and will have to be revisited. Please consider this my best understanding of how to think about AI usage as of Aug. 5 2026.
4334
Andrei Bursuc @abursuc.bsky.social · 05/08/2026
I've always appreciated the different experiments on reviewing done by NeurIPS PCs over the years. However the ever increasing verbosity of rebuttals these days does call for ways to reduce length and the 1 page pdf from CVPR does not look that bad or obsolete.
0173
Reposted by Andrei Bursuc
European Commission @ec.europa.eu · 04/08/2026
It’s hot across Europe right now. Millions of us are feeling it - in cities, towns, and villages across the continent. When heatwaves hit, small actions matter ⬇️
The classic painting "Mary Magdalen in Ecstasy" by Caravaggio, featuring a woman leaning back with eyes closed, with text in white reading: "Feeling the heat today? Follow our safety tips"
1413539
Andrei Bursuc @abursuc.bsky.social · 04/08/2026
Home
4250
Andrei Bursuc @abursuc.bsky.social · 04/08/2026
Tired: Google Summer of Code Wired: NeurIPS Summer of OpenReview Scrolling
180
Reposted by Andrei Bursuc
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 Andrei Bursuc
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
Andrei Bursuc @abursuc.bsky.social · 08/07/2026
The NAVSIM challenges were key to the progress of E2E driving models. But, we start to reach their limits and we need more complex challenges to advance further. The AlpaSim E2E Closed Loop Challenge is a major step. Happy to share that key dates, registration and leaderboard access are now up!
041
Andrei Bursuc @abursuc.bsky.social · 08/07/2026
I've been offline for a few days at a scout camp in a tent. I didn't have much FOMO (still stayed up to date with many things via my phone), but man, does it feel good to be back at my PC!
060
Reposted by Andrei Bursuc
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 Andrei Bursuc
Emma Monk @monkemma.bsky.social · 24/06/2026
35°C is normal, we used to just call that summer! Here's how many summers topped 32°C 70s 4 80s 2 90s 8 2000s 6 2010s all of them 2020s all of them And here's how many summers topped 35°C 70s 1 80s 0 90s 2 2000s 2 2010s 3 2020s 4 (out of 6 so far)
71233430
Reposted by Andrei Bursuc
Nicolas Dufour @nicolasdufour.bsky.social · 19/06/2026
We explored the impact of variability sources in generative modeling. Turns out, we've been neglecting the error bars associated with training variability all along! We should aim to report results that we are sure of their scientific validity, instead of seed engineering!
1174
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
Andrei Bursuc @abursuc.bsky.social · 17/06/2026
Super impressed by how Chinese teams continue releasing super-strong open-weights models! By this time you would assume that private ones are reaching escape velocity thanks to the huge amount of user data and feedback they can harvest, and yet open-models still pop up.
0140
Reposted by Andrei Bursuc
Antoine Guédon @antoine-guedon.bsky.social · 16/06/2026
What if you could turn any number of photos (3, 8, 15, or even 60) into one clean 3D surface (pts & mesh) with Flow Matching? Check out our new work, Surflo: Consistent 3D Surface Flow Model with Global State. 🧵 1/N 🔗https://anttwo.github.io/surflo/
13512