Ben Blaiszik

GitHub - TorchSim/torch-sim: Torch-native, batchable, atomistic simulations. Torch-native, batchable, atomistic simulations. Contribute to TorchSim/torch-sim development by creating an account on GitHub.

Excited to help build the TorchSim community. Reach out to me and join us:

🔸TorchSim GitHub: github.com/torchSim/tor...

🔹TorchSim Slack: join.slack.com/t/torchsim/s...

🔸Hugging Face Science Discord: discord.gg/jDz2UyzQxW

Thanks to the many community contributors already pushing this forward, including Thomas Loux, Ryan Liu, J Kian Pu, Filippo Bigi, Stefan Bringuier, Ph.D. , Myles Stapelberg, Yutack Park, John Gardner, Guillame Fraux, Chuin Wei Tan, and Timo Reents.

But, for more success we now need your help to!
🔷 Build examples, tutorials, and benchmark your workflows
🔶 Integrate new MLIP architectures and optimize GPU utilization
🔷 Implement integrators, optimizers, and simulation methods
🔶 Help document and build this ecosystem.

The original development team, including Abhijeet Gangan, Orion Archer Cohen, Janosh Riebesell, Rhys Goodall, Adeesh Kolluru, Stefano Falletta, and Curtis Chong, Joseph Krause and Jorge Colindres built something special, and we want to ensure their work flourishes.

TorchSim offers faster batched inference, full GPU utilization, and perhaps most importantly, a unified interface across model architectures enabling rapid prototyping and model swapping.

🔥We're excited to announce a major milestone for the machine-learned interatomic potential (MLIP) ecosystem: TorchSim is moving to community ownership and governance through a partnership with Radical AI and the open-source community! TorchSim is an atomistic simulation engine built for the AI era.

This paper won Best Paper Award at EScience 2025, congrats to the entire team team: Marcus Schwarting, @WardLT2, @NCHudson95, Xiaoli Yan, me, Santanu Chaudhuri, Eliu Huerta, @ianfoster
@argonne, @UChicago, @thisisUIC

Applied to MOF discovery, this queue prioritization:
🔶 Doubled discovery of high-performing candidates
🔷 Required <1% extra compute for the RL loop
🔶 Discovered more stable, varied materials

📘 Read the full paper: arxiv.org/pdf/2509.25538

Generative AI is changing how we discover materials, but without direction, it can quickly lose its way. Marcus Schwarting led an effort to show that using active learning as a guide helps to prioritize the best candidates in scientific discovery workflows for MOFs.

Are you looking for ~120~ examples of how LLMs can be used to advance research in materials science & chemistry with open code? We've made a quick search interface for you to explore projects from the recent hackathon.

See the projects here and come join our community: llmhackathon.github.io

Thanks to support from NIST and James Warren for making the MDF vision of vast troves of open data to fuel discovery possible.

We can't wait to see what you build and discover!

Access Details: github.com/facebookrese...

Eagle provides researchers access to high-volume data pioneered by @ianfoster42.bsky.social, Rachana Ananthakrishnan, Kyle Chard, Michael Papka, Rick Stevens, and others. @globusorg.bsky.social provides platform capabilities (auth, data transfer, automation, and compute) to over 600k researchers.

For this first release, the data are quite raw, and as-created by the Meta team. There's an opportunity for the community to build tools that simplify access to these data, allow data query and browsing, create databases of calculated properties and descriptors, and much more.

The Materials Data Facility is proud to make these data available via the Eagle cluster at ALCF through a high-performance Globus endpoint. Given the dataset's scale, we're first releasing data for a 4M random OMol25 split, with the multi-petabyte dataset following based on community engagement.

This dataset includes DFT outputs, electronic densities, wavefunctions, and molecular orbital information for over 4M high-accuracy calculations. We see this as an opportunity to develop higher quality partial charges, partial spins, and advanced electronic features to unlock next generation models.

Data to train next-generation AI models. Data to push the boundaries of what's computationally possible in molecular chemistry and lead the world in AI for science. Data that captures the full complexity of chemical systems, from small organic molecules to massive biomolecular complexes.

We envision a future where researchers can rapidly design molecules and peptides to treat diseases, discover catalysts to revolutionize synthesis and manufacturing, identify the next electrolyte to store and transport energy to protect the grid, and more. But breakthrough discoveries require data.

🔥 Today we announce the Meta OMol25 Electronic Structures Dataset - 500 TB of molecular data in collaboration with the AI at Meta team.

Access Details: github.com/facebookrese...

Going to be honest. Apple’s Liquid Glass and ios26 styling feels cheap and cluttered. Also why would I want to see so much visually distorted content (under glass)?

Some interesting concepts, but needs a lot of work.

Thanks Kyle! More soon…

Ah, you're right. Folders are premium. 🥲

Bookmarks on X are premium tier - which is wild.

Still time to join (event is tomorrow):

Due to overwhelming demand, we are also looking for qualified judges to help if you have an hour or two in the next week and some expertise in materials/chemistry, LLMs, or even with business or previous pitch competitions.

Sign up here: forms.gle/MJNsK5Dvbmvc...

Over 1100 people around the world, virtual and in-person, decided to take a chance together, to imagine, and build - seeking ways to speed discovery and understanding in materials and chemistry with AI.

We'll share our findings soon, but from what I've heard already prepare to be amazed.

Thanks looks cool. :)

Agreed.

My feed has gotten stale. Who is posting top tier science content?

And they’re free too. :)

Read the entire paper and learn about more of our findings here by the amazing team at @argonne @argonne_lcf @UChicago @globus @ianfoster @ENERGY @labsglobus

Read the paper: arxiv.org/abs/2508.18489