YouTube livestream: youtube.com/watch?v=61BeG_…

Transformer-based neural networks achieve impressive performance on coding, math & reasoning tasks that require keeping track of variables and their values. But how can they do that without explicit memory? 📄 Our new ICML paper investigates this in a synthetic setting! 🧵 1/13

What’s next for AI and math trib.al/9cahZIc

After 32 years, I finally had a chance to return to advancing Semiclassical Transition State Theory (SCTST). Check out our paper, just published in The Journal of Chemical Physics (with Alex Popov!) DOE Office of Science #BESfunded doi.org/10.1063/5.0273…

The supervision signal in AI4Science is so crisp that we can solve very complicated problems almost without any data or RL! In this project, we train a model to solve the Schrödinger equation for different molecular conformations using Density Functional Theory (DFT) In the

Most biological processes, like stem cell differentiation, branch into multiple fates, but current trajectory inference methods only predict single paths.🌳To fix this, we introduce BranchSBM 🌿, from our unstoppable Sophia Tang ! 🌟 📜: arxiv.org/abs/2506.09007 💻:

Lecture notes: "Data-driven approaches to inverse problems" (by Carola-Bibiane Schönlieb, Zakhar Shumaylov): arxiv.org/abs/2506.11732 [Comments:Notes from Machine Learning: From Data to Mathematical Understanding (CIME 2023)]

New paper on the generalization of Flow Matching arxiv.org/abs/2506.03719 🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn **can only generate training points**? with Quentin Bertrand, Anne Gagneux & Rémi Emonet 👇👇👇

🚀 After two+ years of intense research, we’re thrilled to introduce Skala — a scalable deep learning density functional that hits chemical accuracy on atomization energies and matches hybrid-level accuracy on main group chemistry — all at the cost of semi-local DFT. ⚛️🔥🧪🧬

If you’re at CTEST and interested in training MLPs with multi-reference electronic structure, check out Laura’s talk on our Weighted Active Space protocol #compchem

Extremely excited to be sharing the output of my internship in Microsoft Research's #AIForScience team: "Understanding multi-fidelity training of machine-learned force-fields" 🤖🧪

Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models. arxiv.org/abs/2506.17139

(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 @ ICML25 of ICML Conference 2025! PITA learns from "hot," easy-to-explore molecular states 🔥 and then cleverly "cools"

Our development of machine-learned transferable coarse-grained models in now on Nat Chem! doi.org/10.1038/s41557… I am so proud of my group for this work! Particularly first authors Nick Charron, Klara Bonneau, Aldo S. Pasos-Trejo, Andrea Guljas.

That's a wrap! The results of the first #cryoEM heterogeneity challenge are up on biorxiv! biorxiv.org/content/10.110…

Lots of hype around multimodal FMs, virtual cells (and labs?), all-atom design...I really think core algorithms (not just scale/integration) will solve the next problems in AIxBio. Take Transition Path Sampling: models transitions for dynamics, optimization, and cell fate. 👇

Do ant colonies work like liquid brains? Check this great paper in pnas, led by CEAB-CSIC Pol Fernandez-Lopez and Frederic Bartumeus, explaining foraging behaviour by modelling ants as mobile neural agents Jordi pnas.org/doi/10.1073/pn…

‘Protein evolution as a complex system’ – A new Comment discusses protein evolution in terms of complex systems theory and machine learning approaches to model the dynamics of protein evolution nature.com/articles/s4158…