1. X
  2. Thomas Kipf
Log inSign up
Thomas Kipf
2,219 posts
Image
user avatar
Thomas Kipf
@tkipf
Sr. Staff RS at @GoogleDeepMind. Gemini Omni Team. Priors: GNNs, Structured World Models, Neural Assets, Veo Ingredients/References, Veo Robotics
San Francisco, CA
scholar.google.com/citations?user…
Joined June 2009
1,428
Following
29.4K
Followers
RepliesRepliesMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    user avatar
    Thomas Kipf
    @tkipf
    May 4, 2020
    My PhD thesis "Deep Learning with Graph-Structured Representations" is now available for download: hdl.handle.net/11245.1/1b63b9… -- It covers a range of emerging topics in Deep Learning: from graph neural nets (and graph convolutions) to structure discovery (objects, relations, events)
    Image
  • user avatar
    Thomas Kipf
    @tkipf
    Jul 7
    Gemini Omni is now available in Adobe Firefly ✨
    user avatar
    Adobe Firefly
    Adobe
    @AdobeFirefly
    Jul 7
    A cat that follows instructions? The possibilities are endless. Gemini Omni Flash now available.
    Image
    00:00
    2.6K
  • user avatar
    Thomas Kipf
    @tkipf
    Jul 6
    If you’re at ICML, make sure to check our poster on “Generation is Required for Data-Efficient Perception”! I won’t be there in person this time, but say hi to @jackhb98 :)
    user avatar
    Jack Brady
    @jackhb98
    Jul 6
    I’m at #ICML2026 presenting our latest work! (Today/Tue 2 pm; Hall A #4016) Encoder-only approaches (e.g. DINO, SigLIP, JEPA) are the dominant paradigm for visual perception. Yet we provide evidence that using a generative decoder may be key for human-like data efficiency! 🧵👇
    Image
    11K
  • user avatar
    Thomas Kipf
    @tkipf
    Jun 24
    I once deeply respected @VoltEuropa and I really hope a paneuropean pro-innovation party can gain more traction in Europe. But whatever led to this statement by Volt on frontier models shows some deeply rooted misinformation / misguidance in the party’s leadership. I hope it’s
    user avatar
    Alex Petropoulos 🤠
    @AlexTPet
    Jun 24
    guys, what are we doing 😭
    Image
    5.9K
  • user avatar
    Thomas Kipf
    @tkipf
    May 29
    Genuinely amazed by how many generalist visual capabilities one can squeeze out of this model
    user avatar
    fofr
    Google AI Studio
    @fofrAI
    May 29
    A quick test of using Omni to edit a video and add labelled bounding boxes around objects. > Add a labelled bounding box around the monster truck and the flag
    Image
    00:00
    8.7K
  • See @tkipf's full profile

    Sign up
    Log in
Advertisement
Advertisement