🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited our paper got accepted and ICML 2025 — and looking forward to discussing this position with other researchers in July. ☺️ We are at a point where these kinds of interactions are extremely relevant in our community! Hope our contribution will foster them even more.

If we're truly making progress, why has the SOTA performance on the Enzymes been declining over the years? 🤔 How is it that replacing the input graph structures with a fixed Cayley graph often performs better? And why are practitioners still relying on vanilla GNNs? 🫣

We're hiring! Come work with me, Tim Sterne-Weiler, and the fantastic teams Genentech Comp Bio / Disco Onc & Prescient Design as a postdoc. Link to apply below 👇

Science agents can automate discoveries from research ideas to wet labs! We show a system of agents (LLMs, diffusion models, hardware equipments) was able to discover and synthesize 5 novel metal-organic structures, going beyond human knowledge. Paper: arxiv.org/abs/2504.14110

😇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!

This is the 2nd true Graph Foundation Model I approve of 👍 (after ULTRA of course, hehe). Great job Kumo!

Introducing Veo Ingredients-to-Video on labs.google/flow Create customized videos from reference images: of people, characters, objects, background, clothing, textures or anything you want! Examples in the thread 🧵

What's the best way to celebrate the NeurIPS deadline and sending papers to anonymous reviewers? Of course by watching an opera about people with gambling problems - season premiere of The Queen of Spades at the Met Opera

After a long hiatus, I've started blogging again! My first post was a difficult one to write, because I don't want to keep repeating what's already in papers. I tried to give some nuanced and (hopefully) fresh takes on equivariance and geometry in molecular modelling.