Profile avatar
tkipf.bsky.social
Research at Google DeepMind. Ex-Physicist. Controllable World Simulators (GNNs, Structured World Models, Neural Assets). 📍 San Francisco, CA
21 posts 5,625 followers 310 following
Regular Contributor
Conversation Starter
Posts 12 Comments 16

Check out @tkipf.bsky.social's post on MooG, the latest in our line of research on self-supervised neural scene representations learned from raw pixels: SRT: srt-paper.github.io OSRT: osrt-paper.github.io RUST: rust-paper.github.io DyST: dyst-paper.github.io MooG: moog-paper.github.io

submitted 45 days ago • 0 comments

I'm excited to announce that I have no idea what day of the week it is and I'm hoping I can keep this up for the rest of the year

submitted 57 days ago • 3 comments

I gave a talk on Compositional World Models at NeurIPS last week 🌐 The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00) Workshop: compositional-learning.github.io

submitted 71 days ago • 1 comment

Blue skies over Joshua Tree 🌌

submitted 90 days ago • 5 comments

Hot take: 90% of what ACs/SACs do could in principle already be automated (with the remaining 10% being process oversight and borderline decision making). At least right now, it seems like reviewers have the more important job for the most part.

submitted 97 days ago • 7 comments

Veo + DreamScreen! www.instagram.com/p/DCpFZ_UMyN...

submitted 98 days ago • 0 comments

Waymo deserves to be the number one tourist attraction in San Francisco right now, and it's not even close For like ~$11 you get to ride in a genuine self-driving car with up to four people! Wildly entertaining

submitted 98 days ago • 10 comments

Being totally obsessed with your work really helps with motivation and with getting things done. Exciting times.

submitted 99 days ago • 3 comments

Let’s welcome @ellis.eu to Bluesky and give them a follow! 🦋

submitted 100 days ago • 0 comments

Hello World!

submitted 103 days ago • 4 comments

Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!

submitted 102 days ago • 18 comments

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. 🧵

submitted 105 days ago • 2 comments