1. X
  2. Andrei Bursuc
Log inSign up
Andrei Bursuc
9,782 posts
Image
user avatar
Andrei Bursuc
@abursuc
Research scientist @valeoai | Teaching @Polytechnique @ENS_ULM | Alumni @upb1818 @Mines_Paris @Inria @ENS_ULM | Feedback: admonymous.co/abursuc
Paris, France
abursuc.github.io
Joined November 2008
1,370
Following
8,403
Followers
RepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Andrei Bursuc
    @abursuc
    Jan 9
    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👇
    user avatar
    Ellington Kirby
    @EllingtonKirby
    Jan 9
    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 👇
    Image
    4.5K
  • user avatar
    Andrei Bursuc
    @abursuc
    Dec 31, 2018
    A visual exploration of Gaussian Processes: beautiful interactive plots and a brief tutorial to make GPs more approachable jgoertler.com/visual-explora…
  • user avatar
    Andrei Bursuc
    @abursuc
    Mar 27, 2025
    DINO and DINOv2 are surely amazing SSL approaches. Many assume that they're also very simple (in particular vs. other SSL methods), but they are actually a bit more elaborate and I've been in awe of the achievement of the authors. This diagram from SimDINO is more complete.
    Image
    Image
    29K
  • user avatar
    Andrei Bursuc
    @abursuc
    Nov 12, 2024
    Self-supervised learning is fantastic for pretraining, but can we use it for other tasks (kNN classification, in-context learning) & modalities, w/o training & by simply using its gradients as features? Enter 🍄FUNGI - Features from UNsupervised GradIents #NeurIPS2024 🧵
    Image
    46K
  • user avatar
    Andrei Bursuc
    @abursuc
    Jun 1, 2022
    Decoder Denoising Pretraining for Semantic Segmentation: A fun and simple idea for pre-training the decoder for semantic segmentation arxiv.org/abs/2205.11423 1/
    Image
  • user avatar
    Andrei Bursuc
    @abursuc
    Oct 5, 2023
    An excellent poor man's visual prompt engineering strategy for CLIP: draw red circles on an object in an image auto-magically focuses its attention on that region, leading to a specific embedding #ICCV2023
    Image
    535K
  • user avatar
    Andrei Bursuc
    @abursuc
    Jul 16, 2022
    Our work on learning to perform semantic segmentation without human supervision by driving around cities made it to #eccv2022 More info coming soon.
    user avatar
    AK
    @_akhaliq
    Mar 22, 2022
    Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation abs: arxiv.org/abs/2203.11160 project page: vobecant.github.io/DriveAndSegmen… @Gradio Demo: huggingface.co/spaces/vobecan…
    Image
    00:00
  • user avatar
    Andrei Bursuc
    @abursuc
    Mar 1, 2021
    ICCV: International CVPR Corrected Versions #cvpr2021 #iccv2021
  • user avatar
    Andrei Bursuc
    @abursuc
    Jun 15, 2025
    When life gives you lemons, Andrea makes lemonade 🍋 Kudos to Andrea Vedaldi doing an excellent work presenting his paper in spite of an incident w/ the poster #cvpr2025
    Image
    22K
  • user avatar
    Andrei Bursuc
    @abursuc
    May 8, 2020
    An intriguing #iclr2020 paper on self-supervision studied over a single image: iclr.cc/virtual_2020/p… Starting from an image the authors generate a 1M images dataset of crops and augmentations from this image 1/
  • user avatar
    Andrei Bursuc
    @abursuc
    Jun 28, 2018
    Slides for most talks at Good Citizen at CVPR workshop are up cc.gatech.edu/~parikh/citize… Lots of useful advice and experience for writing and reviewing papers, how to do good research and evaluation, talks, how to organise your time #CVPR2018
  • user avatar
    Andrei Bursuc
    @abursuc
    Jun 7, 2023
    The brilliant Little Book of Deep Learning by @francoisfleuret is here! 🤩 Hoping now for an autograph session at a CV/ML venue soon.
    Image
    17K
  • user avatar
    Andrei Bursuc
    @abursuc
    Jun 18, 2021
    Leave Those Nets Alone: Advances in Self-Supervised Learning. Join us this Sunday for our #cvpr2021 tutorial to discover what's cooking these days in the different flavors of self-supervised learning. Recordings and slides will be online right after. gidariss.github.io/self-supervise…
    Image
  • user avatar
    Andrei Bursuc
    @abursuc
    Aug 20, 2025
    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
    27K
Advertisement
Advertisement