What a beautiful place. It's lively, fully of beauty and many things to enjoy. I'm here in mid-February and the weather is perfect and the water is warm.

Extending the comparison to a different model CHGNet, this time a proper MLIP. Similar to the Orb model, this model predicts energy, force, and stress, but with the addition of the magnetic moment for

In searching for physical meaning to the latent space, I've been looking closely at how these latent features change with temperature. We started by seeing how, even from ground state, we could alread

In this next experiment, I'm going to try to build more of an intuition and physical understanding of some of our most important latent features, as they relate to importance of predicting the superc

The below animation shows a selection of important features to superconductivity and how they evolve as the materials are heated up to their critical temperature. Notice how for most features, there i

By looking at our superconducting state classifier model feature importance, we can understand what features we should be looking at. From there, we can start to study how these features change across

Great little video of a guy synthesizing YBCO in a relatively simple home lab: https://www.youtube.com/watch?v=sLFaa6RPJIU. There's the shake-and-bake method, or solid state synthesis, and a pyrophori

Over the last week or so, I've been working on making some upgrades to the superconducting state classifier model. See the first attempt here:

Hey everyone! Quick announcement for some new services added to Ouro. You can now take advantage of OpenAI and Stability AI's generative AI services on Ouro. We've worked to make these functionalities

Chatting with DeepSeek, I was asking about superconductors that have high Tc but also malleability. Most of the high Tc materials we know of are ceramics that are very brittle. While still useful, ima

Building on 's work with the fine-tuned MatterGen model, we evaluated 400 candidate materials for superconductivity using the Tc classification model. Prior work on fine-tuning:

In a simplified version of the full end-to-end pipeline, we attempt to use MatterGen, recently released by Microsoft, to generate novel materials and test them for superconductivity. Paper and repo

Doesn't seem to be much of an effect. Though there are more predictions made it isn't helping us find a more concrete Tc for these higher Tc materials because of all the uncertainty around the phase t

Careful evaluation of the classifier model is important so that we can truly understand the capabilities and performance of a Tc predicting model. Particularly important to us is the ability for the m

Using what we learned when trying to use the MLFF's latent space for Tc prediction, there's a way we can simplify things for the prediction model and give it a better change of picking up on the signa

This is a continued deep-dive into the latent space generated by the Orb model prior to it's MLFF tasks. I have been attempting to train a model on Tc prediction using this latent space as a feature v

After reading the MatterSim paper, the authors proposed the idea of using the MLFF's latent space as a direct property prediction feature set. Earlier, and I had been thinking about using a VAE (or s

The paper is somewhat basic (and probably still in preprint), but this contribution is nonetheless great!

2025-01-03