Log inSign up
Alex Kendall
1,224 posts
user avatar
Alex Kendall
@alexgkendall
CEO at @wayve_ai teaching cars how to drive with machine learning πŸ‡³πŸ‡Ώ
London, UK
alexgkendall.com
Joined March 2017
715
Following
17.4K
Followers

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.

TermsΒ·PrivacyΒ·CookiesΒ·AccessibilityΒ·Ads InfoΒ·Β© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Alex Kendall
    @alexgkendall
    Oct 3, 2023
    Today we're announcing #GAIA1: a 9B parameter world model, trained on 4,700 hours of driving data, able to simulate complex and diverse driving scenes from video, text and action inputs. This model is 480x larger than the preview we shared earlier this year and the results are
    00:00
    632K
  • user avatar
    Alex Kendall
    @alexgkendall
    Nov 1, 2022
    This year we’ve seen many incredible AI breakthroughs from very large foundation models: CLIP = image/language Stable Diffusion = caption2image GPT-3 = language Whisper = speech2text etc But what does this mean for robotics and autonomous driving?
  • user avatar
    Alex Kendall
    @alexgkendall
    Nov 22, 2018
    New paper on 3D object detection from monocular images (with no stereo or lidar)! Using geometry to reason in 3D we obtain state of the art for monocular methods on KITTI. Amazing work lead by Tom Roddick at Cambridge. arxiv.org/abs/1811.08188
    00:00
  • user avatar
    Alex Kendall
    @alexgkendall
    Oct 23, 2023
    This is mesmerising! 😎 We're seeing some incredible robust behaviour emerge from our AI Driver. This video shows @wayve_ai's autonomous vehicle driving through London. With no lidar, no HD-maps, no hand-coded rules. Just pure on-board intelligence from our end-to-end neural
    00:00
    279K
  • user avatar
    Alex Kendall
    @alexgkendall
    Apr 13, 2018
    Big update to our work on multi-task scene understanding to be presented as a spotlight at CVPR this year arxiv.org/abs/1705.07115
    GIF
  • user avatar
    Alex Kendall
    @alexgkendall
    Jun 17, 2024
    Today we're announcing PRISM-1πŸ”Ίa breakthrough in dynamic scene reconstruction. This entire video is *simulated* β€” for the first time including dynamic and deformable features like cyclists which was the big blocker to simulating the long-tail. Link to blog in thread. ⬇️
    00:00
    120K
  • user avatar
    Alex Kendall
    @alexgkendall
    Sep 14, 2023
    Language is the future for how we interact with robots. Today @wayve_ai is sharing a first look at LINGO-1, a new vision-language-action AI model. To give you a glimpse of its capabilities, here is a video of me playing with LINGO-1 yesterday morning.
    00:00
    155K
  • user avatar
    Alex Kendall
    @alexgkendall
    Nov 29, 2022
    I’m often asked how does @wayve_ai use simulation to develop our next-generation autonomous driving? Today we’re unveiling Wayve Infinity Simulator for the first time, which we've been building for the last 5 years:
    00:00
  • user avatar
    Alex Kendall
    @alexgkendall
    Jun 21, 2023
    We’ve only had access to GAIA-1 for a few weeks and are discovering new capabilities every day. The results are phenomenal! GAIA isn't just a generative video model, it is a world model, ie. controllable by video, text & action prompts Why is this huge for self driving? Thread:
    00:00
    185K
  • user avatar
    Alex Kendall
    @alexgkendall
    Jun 12, 2023
    I agree with @ylecun and think autonomous driving is the best place to start. As an example, here's a generated video (this is not real!) from our AI's world model showing it is capable of reasoning and imagining about overtaking a bus.
    00:00
    user avatar
    Yann LeCun
    @ylecun
    Jun 11, 2023
    Replying to @geoffreyhinton and @AndrewYNg
    We all agree that we need to arrive at a consensus on a number of questions. I agree with @geoffreyhinton that LLM have *some* level of understanding and that it is misleading to say they are "just statistics." However, their understanding of the world is very superficial, in
    346K
  • user avatar
    Alex Kendall
    @alexgkendall
    May 7, 2024
    Today is a significant milestone for @wayve_ai, as we proudly announce our $1.05 billion Series C from @SoftBank_Group, @Microsoft and @nvidia. Since the start we've held a contrarian belief that end-to-end AI will make autonomy possible. I'm excited about this massive
    117K
  • user avatar
    Alex Kendall
    @alexgkendall
    Jun 9, 2025
    Thank you Prime Minister @Keir_Starmer for hosting us at his house, Chequers. Excited for the announcements we'll be making together this week! πŸ‡¬πŸ‡§ I drove there in our AV without any intervention β€” until the entrance where I had to intervene to be searched by security 😁
    52K
  • user avatar
    Alex Kendall
    @alexgkendall
    Oct 4, 2023
    What’s exciting about #GAIA1 is that it's not just a simulation, but a full world model that understands how the world works Here's two different futures where a reversing car (1) pulls off the street or (2) pulls out suddenly requiring us to brake More of my fav examples in 🧡
    00:00
    199K
  • user avatar
    Alex Kendall
    @alexgkendall
    May 1, 2025
    Here's my favourite scenario from autonomous driving in Tokyo last week! πŸ‡―πŸ‡΅
    00:00
    87K