BioEmu2 is now publicly available! SOO many new things. Now with dynamics trained on a ton of MD simulations. Check it out!
Public preview of BioEmu2! @MSFTResearch AI for Scienceโs new foundation model for biomolecular structure, dynamics and function. Open weights, MIT license.
github.com/microsoft/bioemu2
Movie: BioEmu2-simulated binding of intrinsically disordered peptide PUMA to MCL-1 receptor. ๐งตโฌ๏ธ
Waiting for your MD simulation to finish? Visit our spotlight paper at ICML on how to train large timestep models on existing MLFF datasets in the meantime!
๐๏ธ Wednesday, July 8
โฐ 10:30 AM โ 12:15 PM KST
arxiv.org/abs/2601.22123
Excited to be at ICML with @michaelplainer & @gregorlied to present our ๐ spotlight ๐ paper on Hamiltonian Flow Maps for large-timestep molecular dynamics!
Come say hi at our poster tomorrow or send us a message if you want to chat! ๐ค
๐๏ธ July 8, 10:30 AM โ 12:15 PM
๐ #1306
Excited to share our latest preprint: ๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด ๐๐ฎ๐บ๐ถ๐น๐๐ผ๐ป๐ถ๐ฎ๐ป ๐๐น๐ผ๐ ๐ ๐ฎ๐ฝ๐: ๐ ๐ฒ๐ฎ๐ป ๐๐น๐ผ๐ ๐๐ผ๐ป๐๐ถ๐๐๐ฒ๐ป๐ฐ๐ ๐ณ๐ผ๐ฟ ๐๐ฎ๐ฟ๐ด๐ฒ-๐ง๐ถ๐บ๐ฒ๐๐๐ฒ๐ฝ ๐ ๐ผ๐น๐ฒ๐ฐ๐๐น๐ฎ๐ฟ ๐๐๐ป๐ฎ๐บ๐ถ๐ฐ๐ ๐
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. ๐ก๐ผ ๐ฟ๐ฒ๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ ๐๐ฟ๐ฎ๐ท๐ฒ๐ฐ๐๐ผ๐ฟ๐ถ๐ฒ๐, ๐ป๐ผ ๐๐ป๐ฟ๐ผ๐น๐น๐ถ๐ป๐ด, ๐ป๐ผ ๐๐ฒ๐ฎ๐ฐ๐ต๐ฒ๐ฟ needed!๐งต๐
Michael Plainer retweeted
Fantastic work by Michael Plainer and friends. Energy-based diffusion models to ensure that the denoising distribution equals exp(-u(x)), with the energy u(x). A keystone for connecting molecular dynamics, statistical mechanics and generative AI.
(1/n) Can diffusion models simulate molecular dynamics instead of generating independent samples?
In our NeurIPS2025 paper, we train energy-based diffusion models that can do both:
- Generate independent samples
- Learn the underlying potential ๐ผ
๐งต๐
arxiv.org/abs/2506.17139
Michael Plainer retweeted
(1/n) Can diffusion models simulate molecular dynamics instead of generating independent samples?
In our NeurIPS2025 paper, we train energy-based diffusion models that can do both:
- Generate independent samples
- Learn the underlying potential ๐ผ
๐งต๐
arxiv.org/abs/2506.17139