🔥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

"This is one of the first results where a neural model, when trained to sufficiently low loss, can 𝐠𝐮𝐚𝐫𝐚𝐧𝐭𝐞𝐞 𝐎𝐎𝐃 𝐬𝐢𝐳𝐞 𝐠𝐞𝐧𝐞𝐫𝐚𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 for a non-linear algorithm" ... 🤯

If you're into LLMs, graphs, or just enjoy great talks, Petar Veličković's lecture from our last GLOW session—"LLMs as GNNs"—is now online: youtube.com/watch?v=J1YCdV…

♟️♟️Now our work on teaching superhuman chess strategies to grandmasters (one of whom Gukesh D who became the latest and the youngest world chess champion) is published on PNAS! 🎉🎉 Yes, we can transfer machine knowledge to humans to push the frontier of human. knowledge.

Come to see our papers at #ICLR2025 in Singapore

I want to share a blog post about our paper "All Models are Wrong, Some are Useful: Model Selection with Limited Labels", which we will present at AISTATS Conference 2025 next week With Patrik Okanovic, Jannes Kasper, Torsten Hoefler 🇨🇭, Andreas Krause, Nezihe Merve Gürel (nmervegurel.bsky.social)

Today ICLR 2026 I’ll be at the XAI4Science workshop presenting superstar former MPhil students Batu (now Stanford) and Deepro’s (now Oxford) work on Transformer Attention Graphs for Mechanistic Understanding:

people say GNNs are turning obsolete, but one thing I noticed in my experiments: attention is not so good at picking up local fine-grained details and you need GNNs to do the job! This is because GNNs are a lot more expressive when it comes to pairwise interactions. 1/n

That's next year's GNN course motivating example sorted :)

After supervising 20+ papers, I have highly opinionated views on writing great ML papers. When I entered the field I found this all frustratingly opaque So I wrote a guide on turning research into high-quality papers with scientific integrity! Hopefully still useful for NeurIPS

Course notes: "Optimal Transport for Machine Learners" (by Gabriel Peyré): arxiv.org/abs/2505.06589

Ever wanted to try topological deep learning but felt overwhelmed by the complexity? 👉 Meet TopoTune: a plug-and-play framework that turns any graph neural networks into a topological one! Mathilde Papillon🦋 mathildepapillon .bsky .social Guillermo Bernárdez Claudio Battiloro 🦋 @clabat9.bsky.social Geometric Intelligence Lab Real AI @ UCSB UCSB ECE

We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model. Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO

What does it mean to say "method A works because of reason B" ? In sense of causal inference, if one can intervene the effect of B, and it turns out B causes A, its safe to say "A works well because of B". however, in analysis of ML methods its nearly impossible to do this

dupreeh has officially retired from Competitive Counter-Strike 🥺 "My only goal was just to make a name for myself and I wanted to go out there, and if I could win one Major, that would be the goal for me... And today I stand with five titles"

🚨What is SOTA on tabular data, really? We are excited to announce 𝗧𝗮𝗯𝗔𝗿𝗲𝗻𝗮, a living benchmark for machine learning on IID tabular data with: 📊 an online leaderboard (submit!) 📑 carefully curated datasets 📈 strong tree-based, deep learning, and foundation models 🧵

🚨 Did you know that small-batch vanilla SGD without momentum (i.e. the first optimizer you learn about in intro ML) is virtually as fast as AdamW for LLM pretraining on a per-FLOP basis? 📜 1/n

Today on the blog we share our recent progress in developing graph foundation models that excel on interconnected relational tables and at the same time generalize to arbitrary sets of tables, features, and tasks without additional training. Learn more → goo.gle/4lLPNVe

An advanced version of Gemini with Deep Think has officially achieved gold medal-level performance at the International Mathematical Olympiad. 🥇 It solved 5️⃣ out of 6️⃣ exceptionally difficult problems, involving algebra, combinatorics, geometry and number theory. Here’s how 🧵