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
1,417
Following
29.3K
Followers
Posts
  • 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)
  • user avatar
    Thomas Kipf
    @tkipf
    Dec 4, 2020
    Very excited about the release of Jraph. Finally an easy-to-use, extensive and fast Graph Neural Network library in JAX! Fully compatible with NN libraries such as Flax and Haiku: github.com/deepmind/jraph
  • user avatar
    Thomas Kipf
    @tkipf
    Oct 18, 2018
    DeepMind is releasing their GraphNets library: github.com/deepmind/graph… - a very comprehensive and easy-to-use library for training graph (neural) networks and related models
  • user avatar
    Thomas Kipf
    @tkipf
    Jan 7, 2020
    I’m very excited to announce that I have joined the Google Brain team in Amsterdam 🚲🚣‍♀️🌳 as a Research Scientist! Looking fwd to both continuing my focus on graph-structured representation learning and to explore novel directions with an amazing team of new and old colleagues 😊
  • user avatar
    Thomas Kipf
    @tkipf
    Nov 13, 2024
    The world doesn’t live on a pixel grid and neither should vision models! Excited to share Moving off-the-Grid (MooG): a video model w/o grid-based representations. MooG learns detached “off-the-grid tokens” that bind to (and track) scene elements as camera & content move. 🧵
    00:00
    77K
  • user avatar
    Thomas Kipf
    @tkipf
    Jun 29, 2020
    Excited to share our work @GoogleAI on Object-centric Learning with Slot Attention! Slot Attention is a simple module for structure discovery and set prediction: it uses iterative attention to group perceptual inputs into a set of slots. Paper: arxiv.org/abs/2006.15055 [1/7]
  • user avatar
    Thomas Kipf
    @tkipf
    Jun 15, 2022
    So excited to share Object Scene Representation Transformer (OSRT): OSRT learns about complex 3D scenes & decomposes them into objects w/o supervision, while rendering novel views up to 3000x faster than prior methods! 🖥️ osrt-paper.github.io 📜 arxiv.org/abs/2206.06922 1/7
    00:00
  • user avatar
    Thomas Kipf
    @tkipf
    Apr 23, 2020
    Thanks, @wellingmax, my committee, and everyone who accompanied me through this journey in the last four years!
    user avatar
    Max Welling
    @wellingmax
    Apr 23, 2020
    Congratulations to dr. Thomas Kipf who just successfully defended his thesis through zoom. He graduated CUM LAUDE!!
  • user avatar
    Thomas Kipf
    @tkipf
    Nov 28, 2019
    Excited to share our work on Contrastive Learning of Structured World Models! C-SWMs learn object-factorized models & discover objects without supervision, using a simple loss inspired by work on graph embeddings Paper: arxiv.org/abs/1911.12247 Code: github.com/tkipf/c-swm 1/5
  • user avatar
    Thomas Kipf
    @tkipf
    Jul 18, 2019
    Interested in the latest developments related to Graph Neural Nets and Structured Deep Learning? The talk recordings from the @icmlconf workshop on Learning and Reasoning with Graph-Structured Representations are now available: graphreason.github.io/schedule.html
  • user avatar
    Thomas Kipf
    @tkipf
    Nov 24, 2016
    We are releasing the code for Semi-Supervised Classification with Graph Convolutional Networks (in TensorFlow): github.com/tkipf/gcn
  • user avatar
    Thomas Kipf
    @tkipf
    Dec 9, 2021
    Very honored to receive the ELLIS PhD Award for my thesis on Deep Learning with Graph-Structured Representations -- alongside with with @NagraniArsha for her work on multimodal DL (congrats!)
    user avatar
    Fabian Theis
    @fabian_theis
    Dec 9, 2021
    @ELLISforEurope General Assembly happening just now, with ELLIS PhD Award 2021 to @NagraniArsha and @thomaskipf for very impressive theses on multimodal deep learning and graph NNs, respectively - congrats to both!
  • user avatar
    Thomas Kipf
    @tkipf
    Sep 18, 2023
    Life update: I've moved to the SF Bay Area! Excited to work more closely with my US-based @GoogleDeepMind colleagues and to meet both old and new friends in the area. Leaving Amsterdam wasn't an easy decision: it's such an amazing city with a vibrant ML/AI community. 1/3
    78K
  • user avatar
    Thomas Kipf
    @tkipf
    Jun 28, 2017
    Our implementation of graph auto-encoders (in TensorFlow) is now available on GitHub: github.com/tkipf/gae