Log inSign up
Antoine Yang
183 posts
user avatar
Antoine Yang
@AntoineYang2
Staff Research Scientist @GoogleDeepMind, Gemini video & Omni 🎥. Prev: PhD @Inria & @ENS_ULM, MEng @Polytechnique.
London, England
antoyang.github.io
Joined November 2019
491
Following
1,561
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.

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
    Antoine Yang
    @AntoineYang2
    May 9, 2025
    Thrilled to share our latest advances in video understanding 📽️: Gemini 2.5 Pro is a truly magical model to play with, excelling in traditional video analysis and unlocking new use cases I could not imagine a few months ago🪄 More in 🧵 and @Google blog:
    Google for Developers Blog - News about Web, Mobile, AI and Cloud
    From developers.googleblog.com
    126K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Oct 30, 2023
    Personal update: after 3 wonderful years @Inria, I have joined @GoogleDeepMind full-time as a Research Scientist on the Computer Vision team in London! 🎉
    25K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Mar 12, 2025
    You can now paste YouTube links *directly* to use Gemini audio-video understanding on aistudio.google.com 😀
    8.1K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Oct 10, 2022
    Delighted to share that our paper « Zero-shot Video Question Answering via Frozen Bidirectional Language Models » is accepted at #NeurIPS2022 @NeurIPSConf 😀 w/ @antoine77340, J. Sivic, I. Laptev & @CordeliaSchmid Paper: arxiv.org/abs/2206.08155 Code: github.com/antoyang/Froze… 1/2
  • user avatar
    Antoine Yang
    @AntoineYang2
    Jun 17, 2025
    The newly generally available Gemini 2.5 Flash and Pro are even better at video understanding than the versions we shared in the blog a month ago, see more details in the tech report 😀
    user avatar
    Google DeepMind
    @GoogleDeepMind
    Jun 17, 2025
    Hot Gemini updates off the press. 🚀 Anyone can now use 2.5 Flash and Pro to build and scale production-ready AI applications. 🙌 We’re also launching 2.5 Flash-Lite in preview: the fastest model in the 2.5 family to respond to requests, with the lowest cost too. 🧵
    12K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Mar 1, 2023
    Introducing Vid2Seq, a new visual language model for dense video captioning. To appear at #CVPR2023. Work done @Google w/ @NagraniArsha P.H. Seo @antoine77340 @jponttuset I. Laptev J. Sivic @CordeliaSchmid. Page: antoyang.github.io/vid2seq.html Paper: arxiv.org/abs/2302.14115 🧵/5
    GIF
    13K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Dec 16, 2024
    Gemini 2.0 Flash's video understanding is here 🚀 Think: search in videos via timecodes, extract text from moving camera footage, analyze screen recordings in real-time interactions with native audio out 🔊 Come and try it aistudio.google.com 😀 youtu.be/Mot-JEU26GQ?si…
    aistudio.google.com
    Google AI Studio
    The fastest path from prompt to production with Gemini
    8.7K
  • user avatar
    Antoine Yang
    @AntoineYang2
    May 16, 2025
    Gemini's got a new favorite hobby: reality show analysis! 📺 Gemini 2.5 impressively deciphers long audio-visual content, accurately pinpointing many details of couples' house-buying decisions on a 46-min long British show 😀 Credit: idea from @anna_bortsova 🙌
    00:00
    7.7K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Sep 26, 2023
    🚨 Introducing VidChapters-7M, a large-scale dataset of user-chaptered videos. To appear at #NeurIPS2023 D&B. Work done @Inria w/ @NagraniArsha I. Laptev J. Sivic @CordeliaSchmid Webpage: antoyang.github.io/vidchapters.ht… Paper: arxiv.org/abs/2309.13952 Code: github.com/antoyang/VidCh… 🧵/5
    11K
  • user avatar
    Antoine Yang
    @AntoineYang2
    May 12, 2025
    This week, I'll (try to!) share an example a day of Gemini video understanding capabilities to complement the blog post and ease the wait to I/O 😀 Starting with Gemini counting accurately 22 flag attempt captures in a one-minute video ⛳️
    2.7K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Feb 15, 2024
    Excited to contribute to the launch of a model that can answer detailed questions in videos on a context length that I could have barely imagined when starting to work on video question answering a few years ago 😃 See the report for more details storage.googleapis.com/deepmind-media…
    user avatar
    Sundar Pichai
    Google
    @sundarpichai
    Feb 15, 2024
    As one example of 1.5 Pro’s sophisticated multimodal understanding and reasoning capabilities with long context, when given a 44-minute silent film, the model can analyze various plot points and events, and even makes sense of small details you might have missed.
    00:00
    3.6K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Mar 31, 2022
    Thrilled to announce that our work « TubeDETR: Spatio-Temporal Video Grounding with Transformers » is accepted at @CVPR #CVPR2022 as an Oral! 😀 Joint work with @antoine77340, J. Sivic, I. Laptev and @CordeliaSchmid Paper: arxiv.org/abs/2203.16434 Code: github.com/antoyang/TubeD…
  • user avatar
    Antoine Yang
    @AntoineYang2
    May 9, 2025
    Replying to @AntoineYang2 and @Google
    More importantly, Gemini 2.5 Pro also enables new use cases by seamlessly marrying vision, audio and other structured data formats such as code. For instance, it can transform videos into interactive webpages ⭐️ Try it here: aistudio.google.com/apps/bundled/v…
    GIF
    5.1K
  • user avatar
    Antoine Yang
    @AntoineYang2
    Jun 23, 2023
    Thanks to everyone that stopped by the Vid2Seq #CVPR2023 poster on Wednesday 😀 It was great meeting fellow researchers in these corridors 🙂
    4K