iiinova — where your digital self keeps evolving

Reposted by Thomas Kipf

NeSy 2026 Conference @nesyconf.org · 29/11/2025

Recordings of the NeSy 2025 keynotes are now available! 🎥 Check out insightful talks from @guyvdb.bsky.social, @tkipf.bsky.social and D McGuinness on our new Youtube channel www.youtube.com/@NeSyconfere... Topics include using symbolic reasoning for LLM, and object-centric representations!

youtube.com

NeSy conference

The NeSy conference studies the integration of deep learning and symbolic AI, combining neural network-based statistical machine learning with knowledge representation and reasoning from symbolic appr...

083

Thomas Kipf @tkipf.bsky.social · 27/05/2025

Yes don’t try this at home

050

Thomas Kipf @tkipf.bsky.social · 27/05/2025

Working on Veo's ingredients to video feature has been a blast. Check it out on flow.google

020

Thomas Kipf @tkipf.bsky.social · 27/05/2025

Two life updates: 1) About a year ago I decided to join the Veo team to work on capabilities. It’s been a fun ride! Excited for what’s still to come. 2) I've been busy caring for a newborn the past couple of days 🥰 Excited for the incredible world he will grow up in. Veo's impression below:

5330

Reposted by Thomas Kipf

Mehdi S. M. Sajjadi @msajjadi.com · 13/01/2025

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

srt-paper.github.io

Scene Representation Transformer

0133

Reposted by Thomas Kipf

Maike Osborne @maosbot.bsky.social · 01/01/2025

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

31024

Thomas Kipf @tkipf.bsky.social · 20/12/2024

Congrats!! Lots to think about

020

Thomas Kipf @tkipf.bsky.social · 19/12/2024

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

1404

Thomas Kipf @tkipf.bsky.social · 30/11/2024

That’s a great recommendation, thanks!

010

Thomas Kipf @tkipf.bsky.social · 29/11/2024

Yet our first two days looked like this 😄

120

Thomas Kipf @tkipf.bsky.social · 29/11/2024

Blue skies over Joshua Tree 🌌

5610

Thomas Kipf @tkipf.bsky.social · 25/11/2024

Sending reminders really shouldn’t be something we have to deal with manually. Clearly there’s headroom in designing better incentive structures.

140

Thomas Kipf @tkipf.bsky.social · 25/11/2024

I think there is still *a lot* of headroom for automation while ultimately reducing potential for human error (or just laziness on the AC part).

110

Thomas Kipf @tkipf.bsky.social · 25/11/2024

I think that depends on the conference. ICLR pretty much already automated the reviewer assignment part using a new bidding system that seemed to work pretty well. Manual AC assignments were heavily discouraged, only minor adjustments were needed.

200

Thomas Kipf @tkipf.bsky.social · 22/11/2024

Yeah, it'll have to be a tightly kept secret among people who enter the exclusive AC circle 🙃

030

Thomas Kipf @tkipf.bsky.social · 22/11/2024

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.

7270

Thomas Kipf @tkipf.bsky.social · 21/11/2024

Agreed, important to find the right balance. Deeply caring about something doesn’t mean one should neglect other aspects of life (especially health, sleep, nutrition, social connection, downtime, …).

010

Reposted by Thomas Kipf

Simon Willison @simonwillison.net · 21/11/2024

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

101305

Thomas Kipf @tkipf.bsky.social · 21/11/2024

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

3652

Reposted by Thomas Kipf

Marvin Schmitt @marvin-schmitt.com · 19/11/2024

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

0367

Reposted by Thomas Kipf

ICLR Conference @iclr-conf.bsky.social · 16/11/2024

Hello World!

412833

Reposted by Thomas Kipf

Gabriele Corso @gcorso.bsky.social · 17/11/2024

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!

18610204

Thomas Kipf @tkipf.bsky.social · 15/11/2024

We're planning to open source, but no ETA yet. Stay tuned :)

140

Thomas Kipf @tkipf.bsky.social · 15/11/2024

We'll present this work at NeurIPS (Spotlight, yay 🙌) this year - come find us at the poster soon or reach out if you have questions! This was a fun project with an amazing set of collaborators (and co-leads Sjoerd van Steenkiste and @zdanielz.bsky.social) at Google DeepMind / Google Research.

070

Thomas Kipf @tkipf.bsky.social · 15/11/2024

MooG can provide a strong foundation for different scene-centric downstream vision tasks, including point tracking, monocular depth estimation, and object tracking. Especially when reading out from frozen representations, MooG is competitive with on-the-grid baselines.

110

Thomas Kipf @tkipf.bsky.social · 15/11/2024

Under the hood, MooG uses two independent cross-attention mechanisms to write to – and read from – a *set* of latent tokens that are consistent over time. Think of it as a scene memory consisting of a set of tokens that can flexibly bind to individual scene elements.

120

Thomas Kipf @tkipf.bsky.social · 15/11/2024

Check out the paper & website for emergent scene tracking examples: 📜https://arxiv.org/abs/2411.05927 🌐https://moog-paper.github.io We can visualize token attention to see what part of the scene they take responsibility for – we find that they capture/track the 3D content of the scene.

130

Thomas Kipf @tkipf.bsky.social · 15/11/2024

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. 🧵

27510