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

494 Following

1,585 Followers

Replies Reposts Media

Pinned
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
11
Antoine Yang
@AntoineYang2
Sep 1
Let Gemini choose how to process the video (transcript / audio / which frames) for insane cost / tokens saving esp. for long videos. Super excited to see the new use cases that this will unlock!
Google
@Google
Sep 1
We’re introducing a new capability to our latest Gemini models: agentic video understanding. This allows developers to process long-form video content with more accuracy, while using up to 88% less tokens. See how it works 🧵
Antoine Yang
@AntoineYang2
Jun 10
1H-VideoQA is released today as a Kaggle benchmark! Developed internally in Gemini 1.5 times, it is a rare benchmark to show large scaling of accuracy w/ # linspace frames up to multiple thousands 📈 Grateful to everyone involved, and hope it will be useful to the community 😀
Kaggle
@kaggle
Jun 10
1H-VideoQA is now available on Kaggle Benchmarks! Developed by @GoogleDeepMind back in 2024 (@AntoineYang2) and now updated with latest SOTA models, 1H-VideoQA is a 101-prompt benchmark for long-context video comprehension and temporal episodic reasoning across hour-long YouTube
Antoine Yang
@AntoineYang2
May 20
Combine text, image, audio and video as input to create new videos -- really excited to see what ppl will be able to create with Gemini Omni! 😀
Google DeepMind
@GoogleDeepMind
May 19
We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video. It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵
Antoine Yang
@AntoineYang2
Mar 25
Check the Ego2Web benchmark if you're interested in agents interacting with the Web while being visually grounded in egocentric videos 📽️
Shoubin Yu
@shoubin621
Mar 25
Introducing Ego2Web from Google DeepMind and UNC Chapel Hill, accepted to #CVPR2026. AI agents can browse the web. But can they act based on what you see? Existing benchmarks focus only on web interaction while ignoring the real world. Ego2Web bridges egocentric video

Antoine Yang

Antoine Yang’s posts