Ever get tired of tiny timesteps bottlenecking your MD simulations? We show how to train a model for large-timestep Hamiltonian dynamics directly on standard MLFF datasets. 𝗡𝗼 𝗿𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝘁𝗿𝗮𝗷𝗲𝗰𝘁𝗼𝗿𝗶𝗲𝘀, 𝗻𝗼 𝘂𝗻𝗿𝗼𝗹𝗹𝗶𝗻𝗴, 𝗻𝗼 𝘁𝗲𝗮𝗰𝗵𝗲𝗿 needed! 🧵👇
Thorben Frank
@thorbenfrank.bsky.social
Postdoctoral Researcher @ TU Berlin @BIFOLD Berlin | AI for molecular simulations
If you ever wondered about the pros and cons of Euclidean symmetries in generative models for molecules, stop by at our #NeurIPS poster on Thursday morning 🧬 #AI4Science
Winfried Ripken@winfried-ripken.bsky.social · 8mo agoI’m excited to be at NeurIPS 2025 next week and present our latest paper on molecular conformer generation! Huge thanks to my co-authors @thorbenfrank.bsky.social , Gregor Lied, Klaus-Robert Müller, Oliver Unke and Stefan Chmiela for an incredible collaboration. Supported by: @bifold.berlin
SO3LR is now published in @jacs.acspublications.org ☀️ It’s a pre-trained #ML #forcefield, applicable to #proteins, #glycoproteins and #lipids in explicit water or vacuo. 🧬 Test it right now and run you own simulations 👉 github.com/general-mole... #AI4Science #MachineLearning
Adil Kabylda@kabylda.bsky.social · 11mo agoOur recent work on SO3LR, a general-purpose machine learned force field for molecular simulations, has been published in @jacs.acspublications.org! 🌞 doi.org/10.1021/jacs...
The room I was given to teach #PhysicalChemistry @uoft.bsky.social has no chalkboards 😱 - o tempora, o mores! But then I can just as well record and share my lectures here: youtube.com/playlist?lis...
Introductory Statistical Mechanics - YouTube
CHM328 lectures given at UofT in winter 2025
youtube.com
Microsoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. www.microsoft.com/en-us/resear...
Excited to share our latest work on Euclidean fast attention, which enables learning global atomic representations at linear cost! 🔥 The representations describe the distance and orientation between atoms, crucial for modeling molecular systems tinyurl.com/47xud8nr #MachineLearning #AI4Science
Euclidean Fast Attention: Machine Learning Global Atomic Representations at Linear Cost
Long-range correlations are essential across numerous machine learning tasks, especially for data embedded in Euclidean space, where the relative positions and orientations of distant components are o...
tinyurl.com
The first list filled up, so here's a second list of AI for Science researchers on bluesky. Let me know if I missed you / if you'd like to join! bsky.app/starter-pack...