Faster Training of Neural ODEs Using Gauß–Legendre Quadrature Alexander Luke Ian Norcliffe, Marc Peter Deisenroth. Action editor: Kevin Swersky. openreview.net/forum?id=f0FSD… #odes #sde #sdes

Excellent work by Alexander Norcliffe !

🎉Very happy to announce that Sheaf Hypergraph Networks got accepted to #NeurIPS2023. Many thanks to my collaborators @glcssr Fabrizio Silvestri Pietro Lio'. 📜arxiv.org/abs/2309.17116 Details 👇🏻 1/4

Benchmarking Continuous Time Models for Predicting Multiple Sclerosis Progression Alexander Luke Ian Norcliffe, Lev Proleev, Diana Mincu et al.. Action editor: Qibin Zhao. openreview.net/forum?id=2uMnA… #sclerosis #models #predict

Exciting development in our faculty: Sarah Teichmann has been elected as Professor in Stem Cell Medicine at Cambridge Stem Cell Institute and will move to the Biomedical Campus with her group Teichlab. Congratulations! Read more: ccaim.cam.ac.uk/faculty-member…

Super excited to finally release our "Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems" !🤗 Link: arxiv.org/pdf/2312.07511… Written with Chaitanya K. Joshi Simon Mathis Victor Schmidt 💀🐔 Santiago Miret Fragkiskos Malliaros Taco Cohen Pietro Lio, Yoshua Bengio Michael Bronstein 😍 See thread below 👇 (1/8)

We just released a "Hitchhiker's Guide" for getting started with deep neural nets for 3D structural biology & chemistry -- we hope it will be useful for newcomers! 🤗 Learn about the core architectures powering protein design, material discovery, molecular simulations, and more!

Sharing a surprising result on AI molecule generation with Transformers: All-atom DiT with minimal molecular inductive bias is on par with SOTA equivariant diffusion (SemlaFlow, a very strong and optimized model) Scaling pure Transformers can alleviate explicit bond prediction!