Postdoctoral Researcher @ TU Berlin @BIFOLD Berlin | AI for molecular simulationshttps://bsky.app/profile/thorbenfrank.bsky.socialhttps://bsky.app/profile/thorbenfrank.bsky.social/post/3m6rpachmwk22If 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 [contains quote post or other embedded content]29 Nov 2025 15:21 +0000at://did:plc:5cdde2y2sgbotyer2gxy2yke/app.bsky.feed.post/3m6rpachmwk22https://bsky.app/profile/thorbenfrank.bsky.social/post/3lydbwfrx4k25SO3LR 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 👉 https://github.com/general-molecular-simulations/so3lr #AI4Science #MachineLearning [contains quote post or other embedded content]08 Sep 2025 13:14 +0000at://did:plc:5cdde2y2sgbotyer2gxy2yke/app.bsky.feed.post/3lydbwfrx4k25https://bsky.app/profile/thorbenfrank.bsky.social/post/3leuhrnep622uExcited 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 https://tinyurl.com/47xud8nr03 Jan 2025 20:50 +0000at://did:plc:5cdde2y2sgbotyer2gxy2yke/app.bsky.feed.post/3leuhrnep622u