Jacob Bamberger

@jacobbamberger

Looking for geometry where it shouldn’t be. PhD student @CompSciOxford. Interested in Geometric Deep Learning

Joined June 2020

627Following

229Followers

Pinned

Jacob Bamberger@jacobbamberger · Jul 13

🚨 ICML 2025 Paper 🚨 "On Measuring Long-Range Interactions in Graph Neural Networks" We formalize the long-range problem in GNNs: 💡Derive a principled range measure 🔧 Tools to assess models & benchmarks 🔬Critically assess LRGB 🧵 Thread below 👇 #ICML2025

jacobbamberger's tweet image. 🚨 ICML 2025 Paper 🚨

"On Measuring Long-Range Interactions in Graph Neural Networks"

We formalize the long-range problem in GNNs:
💡Derive a principled range measure
🔧 Tools to assess models &amp; benchmarks
🔬Critically assess LRGB

🧵 Thread below 👇
#ICML2025

7.0K

Jacob Bamberger Retweeted

Scott le Roux@leRoux_Scott · Jul 17

Interested in Long-Range Interaractions ? Come speak with us now (4:30pm-7pm) at our poster E-2802 @ #ICML2025 @benpgutteridge @jacobbamberger @mmbronstein @epomqo

2.0K

Jacob Bamberger Retweeted

Alex Tong@AlexanderTong7 · Jul 16

Come check out SBG happening now! W-115 11-1:30 with @charliebtan @bose_joey Chen Lin @leonklein26 @mmbronstein

6.0K

Jacob Bamberger Retweeted

Michael Bronstein@mmbronstein · Jul 15

5. On Measuring Long-Range Interactions in Graph Neural Networks East Exhibition Hall A-B #E-2802 Wed 16 Jul 4:30 p.m. PDT @jacobbamberger @benpgutteridge @leRoux_Scott @epomqo

541

Jacob Bamberger Retweeted

Learning on Graphs Conference 2025@LogConference · Jul 11

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

11.0K

Jacob Bamberger@jacobbamberger · Jul 13

🚨 Excited to announce that "How Expressive are Knowledge Graph Foundation Models?" is coming to ICML 2025! 🎉 📅 Wednesday, July 16th 🕟 4:30 PM 📍 Booth #E-3011 Come by to chat about motifs, expressiveness, and the future of graph foundation models! 🔍📊🔗

XXingyue Huang @ ICML 2025@hxyscott · Feb 24

Knowledge Graph Foundation Models (KGFMs) are at the frontier of graph learning - but we didn’t have a principled understanding of what we can (or can’t) do with them. Now we do! 💡🚀 🧵 with Pablo Barcelo, @ismaililkanc, @mmbronstein, @michael_galkin, @JuanLReutter, @OrthMiguel

123

18.0K

Jacob Bamberger Retweeted

Symmetry and Geometry in Neural Representations@neur_reps · Jul 8

📢 Call for Papers: NeurReps 2025 ‼️‼️‼️ 🧠 Submit your research on symmetry, geometry, and topology in artificial and biological neural networks. Two tracks: Proceedings (9 pages) and Extended Abstract (4 pages). Deadline: Aug 22, 2025. neurreps.org/call-for-papers

175

28.0K

Jacob Bamberger Retweeted

Kirill Neklyudov@k_neklyudov · Jun 24

(1/n) Sampling from the Boltzmann density better than Molecular Dynamics (MD)? It is possible with PITA 🫓 Progressive Inference Time Annealing! A spotlight @genbio_workshop of @icmlconf 2025! PITA learns from "hot," easy-to-explore molecular states 🔥 and then cleverly "cools"…

301

257

43.0K

Jacob Bamberger Retweeted

Adam Gosztolai@AGosztolai · Jun 5

🚀🚀Thrilled to announce that my lab has secured generous funding of 1.6m EUR from the Vienna Science and Technology Fund (wwtf.at/funding/progra…)! We have #PhDposition, #postdocjobs and #internships in robotics/ML to work towards a foundation model of macaque locomotion!

924

Jacob Bamberger Retweeted

Ali Hariri@haririAli95 · Jun 11

📢ChebNet is back—with long-range abilities on graphs !🎉 We revive ChebNet for long-range tasks, uncover instability in polynomial filters, and propose Stable‑ChebNet—a non-dissipative dynamical system with controlled, stable info propagation 🚀 📄: arxiv.org/abs/2506.07624

4.0K