We introduce Spatio-Spectral GNNs (S²GNNs) – an effective modeling paradigm via the synergy of spatially and spectrally parametrized graph conv. S²GNNs generalize the spatial + FFT conv. of State Space Models like H3/Hyena. Joint work w/ Arthur Kosmala Daniel Herbst Stephan Günnemann

Check out this new work done jointly w/ Simon Geisler Daniel Herbst Stephan Günnemann (cf. main tweet below). We explore the benefits of adding a classic polynomial (i.e., spatial) GNN and a filter that is directly parametrized (and, thus, highly discriminative) in the spectral domain.

📢 BIG ANNOUNCEMENT NewInML is back at NeurIPS Conference on Dec 10th! Join us for insights from 3 incredible speakers: Tom Goldstein Maarten Sap (he/him) and Kaiming He! We will share about the world of ML research. Check out the agenda below and do not miss it! 👇 #NeurIPS2024 #NewInML

Make sure to stop by our #NeurIPS poster on Spatio-Spectral Graph Neural Networks (S²GNNs)! An efficient synergy of spatially & spectrally parametrised graph convolutions. Joint work w/ Simon Geisler Daniel Herbst Stephan Günnemann. 📎 openreview.net/pdf?id=Cb3kcwY… 📆 Dec 13, 11am, #4608

We’re thrilled to share that the first in-person LoG conference is officially happening December 10–12, 2025 at Arizona State University logconference.org Important Deadlines: Abstract: Aug 22 Submission: Aug 29 Reviews: Sept 3–27 Rebuttal: Oct 1–15 Notifications: Oct 20

🔥 New workshop at NeurIPS Conference! DiffCoALG bridges the gap between classic algorithms & differentiable learning. Think: LLM reasoning, routing, SAT, MIP — neurally optimized end-to-end. 📌 Submit by Aug 22! 🔗 sites.google.com/view/diffcoalg… #NeurIPS2025

📢 NeurIPS Fast Track at LoG 2025 📢 Got a #NeurIPS2025 rejection? 😢 Don’t worry—LoG 2025 has you covered! 🚀 Submit your NeurIPS paper (≥ avg score 4.0) for a Fast Track chance to shine! 🗓️ Deadline: Sept 29, 2025 📍 OpenReview: tinyurl.com/LoG-NeurIPS-Tr…

🚨 Keynote lineup for #LoG2025! 🚨 Thrilled to welcome these amazing pioneers! 🚀 - Aditi S. Krishnapriyan Aditi Krishnapriyan (UC Berkeley) - Haggai Maron Haggai Maron (Technion / NVIDIA) - Melanie Weber Melanie Weber (Harvard) - Michael Galkin Michael Galkin (Google)