Applying machine learning to challenges in materials science.
Senior Researcher at Microsoft research AI for Science.
Views are my own
Claudio Zeni
Loading...
This was a highly collaborative and interdisciplinary effort led by Microsoft AI for Science in partnership with Microsoft Research Accelerator and collaborators at the , University of Illinois Urbana-Champaign and University of California Davis.
(6/6)
⚡️ Faster simulation: We have accelerated MatterSim-v1 model inference by 3-5x and integrated it with the LAMMPS software package, enabling large-scale simulations across multiple GPUs.
(4/6)
🔬 Experimental validation: Using high-throughput screening with MatterSim-v1, we have identified and experimentally synthesized tetragonal TaP, with thermal conductivity (152 W/m/K) close to the one of silicon.
(3/6)
#MatterSim keeps getting better!
👩🔬 Experimentally synthesized high thermal conductor identified by MatterSim
⚡️ 3-5x inference speed-up
💪 MatterSim-MT: a new multi-task foundation model for in silico materials characterization
⬇️ Details below (1/6)
#materials #mlip #lammps
💪 New model: We are introducing MatterSim-MT, a multi-task foundation model for in silico materials characterization that enables the simulation of complex, multi-property phenomena beyond what potential energy surfaces alone can capture.
(5/6)
Blog post: www.microsoft.com/en-us/resear...
MatterSim v1 GitHub: github.com/microsoft/ma...
MatterSim-MT: arxiv.org/abs/2605.079...
(2/6)
📢 New Postdoc position
We just opened a 2-year ML Postdoc position at @msftresearch.bsky.social AI for science.
Come work with us on exciting challenges in #materials
Link to job application:
apply.careers.microsoft.com/careers/job/...
Check out these exciting news about our MatterSim model!
