A little late, but happy to announce that our paper on Rough Transformers ⛰️ has been accepted at NeurIPS Conference! We present a way to make Transformers for temporal data more efficient and robust to irregular sampling through path signatures! Read on! #neurips2024 (1/7)

Fisher Flows for discrete generative modeling led by Oscar Davis arxiv.org/abs/2405.14664

Fisher Flow Matching for Generative Modeling over Discrete Data nips.cc/virtual/2024/p… Oscar Davis Samuel Kessler Mircea Petrache İsmail İlkan Ceylan Joey Bose

Fisher Flow Matching, NeurIPS East right now!! Poster number 2606 Joey Bose

Vienna #sciball ⁦Oscar Davis⁩ ⁦Joey Bose⁩

🍩 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.

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, İsmail İlkan Ceylan, Michael Bronstein, Michael Galkin, Juan Reutter, Miguel

New preprint! 🚨 We scale equilibrium sampling to hexapeptide (in cartesian coordinates!) with Sequential Boltzmann generators!  📈 🤯 Work with Joey Bose, Chen Lin, Leon Klein, Michael Bronstein and Alex Tong Thread 🧵 1/11

NeurIPS'24 has over 4k papers! Below is my selection of 5 papers which considers information geometry: 1/ arxiv.org/abs/2405.16441 2/ arxiv.org/abs/2411.02623 3/ arxiv.org/abs/2405.14073 4/ arxiv.org/abs/2411.00680 5/ arxiv.org/abs/2405.14664

Great final lecture in Michael Bronstein GDL course given by Joey Bose 🚀feat famous smiley gif by Oscar Davis 😄

Excited to release FORT, a new regression-based approach for training normalizing flows 🔥! 🔗 Paper available here: arxiv.org/abs/2506.01158 New paper w/ Oscar Davis Jiarui Lu Jian Tang Michael Bronstein Yoshua Bengio Alex Tong Joey Bose 🧵1/6

🎉Personal update: I'm thrilled to announce that I'm joining Imperial College London Imperial College London as an Assistant Professor of Computing Imperial Computing starting January 2026. My future lab and I will continue to work on building better Generative Models 🤖, the hardest

🚨 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! 🔍📊🔗

🚨 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

GenBio Workshop ORAL Presentation 📜 Title: FORT: Forward-Only Regression Training of Normalizing Flows 🕐 When: Fri 18 Jul 🗺️ Where: East Exhibition Hall A 🔗 arXiv: arxiv.org/pdf/2506.01158 w/ Danyal Rehman Oscar Davis Jiarui Lu Jian Tang Michael Bronstein Yoshua Bengio

Wrapping up #ICML2025 on a high note — thrilled (and pleasantly surprised!) to win the Best Paper Award at GenBio Workshop @ ICML25 🎉 Big shoutout to the team that made this happen! Paper: Forward-Only Regression Training of Normalizing Flows (arxiv.org/abs/2506.01158) Mila - Institut québécois d'IA

Apply for the AITHYRA-CeMM International PhD Program! 15-20 fully funded PhD fellowships available in Vienna in AI/ML and Life Sciences Deadline for applications: 10 September 2025 apply.cemm.at

📢Interested in doing a PhD in generative models 🤖, AI4Science 🧬, Sampling 🧑‍🔬, and beyond? I am hiring PhD students at Imperial College London Imperial Computing for the next application cycle. 🔗See the call below: joeybose.github.io/phd-positions/ And a light expression of interest:

Very excited to share this! We introduce a new approach to knowledge graph foundation models built on probabilistic equivariance. The model is simple, expressive, and probabilistically equivariant — and it works remarkably well! Collaboration led by Jinwoo Kim and Xingyue Huang.

As the IMM paper came out in March, I implemented it myself for some project, before the true source code was made available. I am releasing my version now: github.com/olsdavis/imm It contains most/all features, and should be easy to (re-)use! Hope someone finds it helpful 🙂