We are open-sourcing the code for our CO paper! It is built with #PyTorch, #PyTorchLightning, #PyTorchGeometric a pinch of #JAX and of course... #CLRS30 The NAR part should also be extensible, so feel free to reuse it for your next NAR project. github.com/danilonumeroso…

Here are the top 10 reviewers for LoG 2023, as chosen by the community! Congratulations to everyone, and thank you for your contribution to LoG! 🤗 Dobrik Georgiev Alex Morehead (何聪) Francesco Di Giovanni Yunan Luo Rishi Sonthalia Giorgos Bouritsas (@[email protected]) Arjun (is no longer on this site) J. Nastos C. Bravo-Hermdorff, R. Abboud

Super excited to finally release our "Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems" !🤗 Link: arxiv.org/pdf/2312.07511… Written with Chaitanya K. Joshi Simon Mathis Victor Schmidt 💀🐔 Santiago Miret Fragkiskos Malliaros Taco Cohen Pietro Lio, Yoshua Bengio Michael Bronstein 😍 See thread below 👇 (1/8)

We just released a "Hitchhiker's Guide" for getting started with deep neural nets for 3D structural biology & chemistry -- we hope it will be useful for newcomers! 🤗 Learn about the core architectures powering protein design, material discovery, molecular simulations, and more!

The perfect lecture doesn’t exi….

Many asked about our Computational Biology Workshop at #ICML2024. 6 years' service and a score of 8.7 this year, we weren’t selected, despite an acceptance score of 7.0. Repeated attempts to contact ICML chairs have gone unanswered. Transparency & communication matter ICML Conference.

Thanks to everyone who came out to the Valence Labs TechBio social last night ICLR 2026! It was great to meet with so many researchers working at the intersection of AI and drug discovery If you weren't able to get a spot, DM me! We're having a small dinner tomorrow 🍲

(1/2) The Learning on Graphs Conference 2025 is the leading conference dedicated to graph machine learning. The third edition is not happening this year, but next year (2025). Don't be too sad though, we are preparing something even bigger: there is going to be an in-person main event at UCLA. If

LoG Conference 2024 is back !!!👉 We are looking for more reviewers! We have a special emphasis on review quality via monetary rewards, a more focused conference topic, and low reviewer load (max 3 papers). But for this we need your help! Sign up here: forms.gle/Nuff4ndVZDFTis…!

Curious about how learning to prevent failures happening into a system while having interpretability and formal guarantees? Then, have a look at our paper "Learning What to Monitor: Using Machine Learning to Improve past STL Monitoring", presented this week at #IJCAI24 #AI

#neurips2024 will be very DEAR to me this year! Deep Equilibrium Algorithmic Reasoning has also been accepted at NeurIPS after its selection for an oral presentation at MAR@CVPR 2024. Special thanks to my collaborators Davide Buffelli Pietro Lio' and, my lucky charm, JJ Wilson!

.Pietro Lio' (Cambridge) "Actionable Geometric Deep Learning in Medicine" There’s no one better than Pietro to kick off the IMS workshop on Applied Geometry for Data Science! ims.nus.edu.sg/events/applied…

I'll be at NeurIPS next week presenting two papers (on the generalization of 2nd order methods, and on a new model for Neural Algorithmic Reasoning). Feel free to reach out if you'd like chat about optimization, graphs, foundation models for time series, or AI 4 chip design

Thanks for showing us around University of British Columbia, Hamed Shirzad TIL that our #NeurIPS posters will be actually side (3009) by side (3010). Coincidence? 😀

So it begins... East, poster sess 3, 3009 #NeurIPS2024

Our first attempts at mechanistic interpretability of Transformers from the perspective of network science and graph theory! A wonderful collaboration with superstars Batu El, Deepro Choudhury, Pietro Lio' as part of the Geometric Deep Learning class at Cambridge Computer Science!

Introducing All-atom Diffusion Transformers — towards Foundation Models for generative chemistry, from my internship with the FAIR Chemistry team FAIR Chemistry AI at Meta There are a couple ML ideas which I think are new and exciting in here 👇