🔥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

"Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality" by Josh Southern, Yam Eitan, Guy Bar-Shalom, Michael Bronstein, Haggai Maron, Fabrizio Frasca Paper: arxiv.org/abs/2501.03113 #graphneuralnetworks

🚀 Announcing the Weight Space Learning Workshop at #ICLR2025 ICLR 2026 When neural nets are trained, it’s the weights that embed all the information. Our workshop explores treating these weights as new data modality. Interested? Join us in Singapore! weight-space-learning.github.io

Our **Flow Matching Tutorial** from #NeurIPS2024 is now publicly available: neurips.cc/virtual/2024/t… Heli Ben-Hamu Ricky T. Q. Chen

🚀 ICLR 2026 notification, 🚀 #CVPR2025 rebuttal, 🚀 ICML Conference submission - nothing is as fun as submitting a paper to our 🔥 Weight Space Learning Workshop 🔥 at ICLR 2026 Interested? Have a look at: weight-space-learning.github.io Konstantin Schürholt,Giorgos Bouritsas (@[email protected]), Eliahu Horwitz,

🚀 Our code and data are now live! Explore them here: github.com/NVlabs/tracks-… 📌🔥 #4DTracking

⏳Final hours to submit to the 1st workshop on Weight Space Learning at #ICLR2025 @ICLR_conf❗ 🚀Explore learning directly from model weights! 🌐 weight-space-learning.github.io ⏰ Submit by Feb 10 2025 AoE

🍩 Topological blindspots is coming to ICLR as an oral presentation! 🍩 We prove that message-passing based topological deep learning (TDL) architectures are unable capture basic topological invariants including homology, orientability, planarity and more.

GLOW is back 𝐭𝐡𝐢𝐬 Wednesday, 🗓️ Februrary 19th, 5pm CET 🌟 Before our returning to our regular format in March, we’re hosting an open discussion on where Graph Learning is headed and where early-career researchers can make the most impact. [1/3]

📢🔥 If you like to learn about "Proteina", I will be presenting the work in the Machine learning for protein engineering seminar seminar series later today at 1pm PT / 4pm ET. I hope to see you there! 😀

Highly recommend Fabri as a mentor!

* Graph Learning Will Lose Relevance Due To Poor Benchmarks * Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca, Luis Muller, et al. Inc. Michael Bronstein Bryan Perozzi Michael Galkin Christopher Morris Wow we should be discussing / acting on this!

We should host more top ML conferences (ICLR, ICML, NeurIPS) in Asia

What if models could be the data🤔Find out at ICLR 2026 #ICLR2025 Join the 1st workshop on Model Weights as a New Data Modality. We're training networks on model weights for a wide variety of tasks. Featuring an amazing lineup of papers & speakers🚀 🗓️Sunday 9-17 📍Topaz 220-225

Come join us tomorrow for this amazing workshop!!!

📢 Introducing: Learning on LLM Output Signatures for Gray-box LLM Behavior Analysis [arxiv.org/pdf/2503.14043] A joint work with Fabrizio Frasca (co-first author) and our amazing collaborators: Derek Lim Yoav Gelberg Yftah Ziser Ran El-Yaniv Gal Chechik Haggai Maron 🧵Thread

Check out our new paper on learning from LLM output signatures: the |tokens| x |vocab|+1 matrix of predicted next-token probs and actual next-token prob. It provably generalizes several existing approaches and is great at hallucination / data contamination detection tasks!

Our inaugural workshop on weight space learning at ICLR in Singapore has started! Join us in Topaz 220-225 to talk all things NN weights and check weight-space-learning.github.io!

🚨Tutorial on Positional and Structural Graph Representations invariances.org/graph-represen… Given at the National Institute for Theory and Mathematics in Biology. Thanks to Claire Donnat and Olga Klopp for the invitation! Haggai Maron, the tutorial is finally out!