Stop watching videos, start interacting with worlds. Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!

“Do you know what they call the Rizzler in France?” “They don’t call him the Rizzler?” “No. They call him Le Charismeur”

The Learning on Graphs Conference 2025 Montreal meetup was a great success! Big thanks to my co-organizers Jama Mohamud and Liheng Ma, the presenters and all attendees!

Our massive 60-pager survey is finally published at TMLR with the 🌟 Survey Certification 🌟 after 1.5y of revisions. Graph learning and DL in general have changed a lot since the time we started this project

i am about to teach a new applied linear algebra course at Penn Engineering, meant for datasci/ML/AI. to support the class, i've written a book... [see below for links to text]

🚨 The 8th annual Graph Signal Processing Workshop is back this May 14-16! Held in Montreal, CA, at Mila - Institut québécois d'IA, we’re covering all things graphs, signals, learning, & applications 🕸️〰️ 🔗: gspworkshop.org 👉🏻Abstract submission opens Feb 1 👉🏻 Registration opens Mar 20

We’re absolutely thrilled to have an exciting lineup of speakers this year covering a wide range of topics, including Bastian Grossenbacher-Rieck, Dominique Beaini, Mathilde Papillon🦋 mathildepapillon .bsky .social, Dhananjay Bhaskar, Danai Koutra, and Naoki Saito 🎙️

🚨 Our Call for Reviewers is finally open!! We invite members of the community from *ALL* levels with relevant backgrounds to help review for the GSP Workshop 2025 📝 Sign up here 👇🏻👇🏻👇🏻 forms.gle/Qc3Gfz3sax2y3s… Looking forward to having you join the reviewing team ⚡️

🚨 We're thrilled to partner with Transactions on Machine Learning Research and are introducing a TMLR-to-GSP track 🥳🤝🏻 👉🏻 Papers accepted into TMLR about GSP will be presented at the GSP Workshop! 🔗 Register your interest in sharing your work through this track: docs.google.com/forms/d/e/1FAI… Spread the word 🙌🏻

From mazes to bacteria like structures, the Gray-Scott reaction-diffusion model reveals how small tweaks to diffusion rates (Du, Dv) and reaction parameters (F, k) produce different emergent morphologies. Mathematical beauty in action! Made with #python #matplotlib #mlx

AI cannot destroy the understanding you gain from a work; it can’t understand things for you. If you’re worried about the economic effects of AI, fine—but if the market value of a piece of cultural or scientific work is its primary value to you, you’ve already lost the plot.

🥳🎉 Decisions for GSP Workshop '25 are finally out!! Heartiest congratulations to all accepted papers – we're thrilled to have you join us in Montreal this summer 🙌🏻 We'll announce the full program and release ticketing information soon, so do stay tuned! #gsp2025

😇Hijacking this great thread to talk about a potential way to _identify_ problems with existing benchmarking datasets (also to appear in ICML 2025): arxiv.org/abs/2502.02379 TL;DR: We look at how "graphical" graph benchmarking datasets are. Spoiler: less than you'd hope for!

It's almost time for #GSP2025 ⏱️🥳 We're super excited to host you at Mila - Institut québécois d'IA this coming Wednesday, 14th May! Hope those posters are coming along 😉 👉🏻 FYI: Registrations are still open, so we encourage you to visit our website for details: gspworkshop.org

*sniff* *pulls shirt* You know, this is perfect - *gestures wildly* - this is the ultimate perversity of capitalism at its purest. Here we have Anthropic, this company claiming to build "AI for humanity," and what do they do? They create this digital cocaine, this Claude Code,

this mustafa suleyman blog is SO interesting — i'm not sure i've seen an AI leader write such strong opinions *against* model welfare, machine consciousness etc mustafa-suleyman.ai/seemingly-cons…

Enjoyed giving our tutorial on Geometric & Topological Deep Learning at IEEE MLSP 2025 alongside Semih Cantürk. Loving the Istanbul vibes and the amazing food here! ✅

We are organizing the CoLearn workshop in Aachen (colearn.rwth-aachen.de), fostering exchange between combinatorial optimization and machine learning, with a fantastic keynote speaker lineup, including @69aLodi, N. Megow, M. Skutella, G. Schäfer, Y. Zhang, and J. Toenshoff.

Hello everyone. A friend told me that I shouldn't post this message because it made me and other PhD students look bad. But I actually think it's important to show how PhD students (especially foreign ones) have to deal not only with research-related difficulties, but also with

Recordings for the talk on "Tiny Recursive Models" are up. youtu.be/ETukUNsn_wQ