CIF file for ZrFe12Si2B, a ferrimagnetic materials from Materials Project. https://next-gen.materialsproject.org/materials/mp-653838
A 3D interactive scatter plot of magnetic materials from Materials Project. Points are colored by the materials estimated magnetic density and poitioned by UMAP reduction of Orb v2 model latent space
The crystal structure of a neodymium magnet. It is a permanent magnet made from an alloy of neodymium, iron, and boron to form the Nd2Fe14B tetragonal crystalline structure. They are the most widely used type of rare-earth magnet.
Room-temperature ferromagnets are high-value targets for discovery given the ease by which they could be embedded within magnetic devices. However, the multitude of potential interactions among magnetic ions and their surrounding environments renders the prediction of thermally stable magnetic properties challenging. Therefore, it is vital to explore methods that can effectively screen potential candidates to expedite the discovery of novel ferromagnetic materials within highly intricate feature spaces. To this end, the authors explore machine-learning (ML) methods as a means to predict the Curie temperature (Tc) of ferromagnetic materials by discerning patterns within materials databases.
Atomistic modelling of magnetic materials provides unprecedented detail about the underlying physical processes that govern their macroscopic properties, and allows the simulation of complex effects such as surface anisotropy, ultrafast laser-induced spin dynamics, exchange bias, and microstructural effects. Here the authors present the key methods used in atomistic spin models which are then applied to a range of magnetic problems. They detail the parallelization strategies used which enable the routine simulation of extended systems with full atomistic resolution.
Generated image from "Crowded dance floor seen from above, with clusters of dancers all performing identical synchronized movements within their groups. The dance moves are visibly spreading from dancer to dancer like a wave, with clear boundaries between different dance styles." using DALL-E 3 from OpenAI.
Generated image from "A time-lapse of a stadium doing increasingly energetic waves. In the first frame, a perfect grid of glowing points shows almost perfect alignment. As the wave intensifies in subsequent frames, the points become increasingly chaotic and misaligned, eventually showing completely random orientations at the height of the wave's energy." using DALL-E 3 from OpenAI.
Generated image from "A bookshelf with various books - thin paperbacks laying flat, tall encyclopedias standing upright, and a few books precariously balanced on their edges or covers. An invisible force appears to be trying to rotate the books, with the encyclopedias strongly resisting the rotation while the paperbacks easily change orientation." using DALL-E 3 from OpenAI.
Generated image from "A political map showing a country divided into distinct districts, each colored either red or blue. Some areas show large unified blocks of a single color, while boundaries between differently colored regions are clearly visible. A giant hand is holding a magnet above the map, causing more districts to align to the same color" using DALL-E 3 from OpenAI.
Generated image from "Only visualize this idea. No text. Imagine a dance floor with a simple rule: dancers (electrons) with the same moves (spins) need more space between them due to social etiquette (Pauli exclusion principle). In ferromagnetic materials: When two dancers meet, it's energetically favorable for them to dance the same way (parallel spins) As one dancer starts doing a specific move, nearby dancers naturally follow along This creates "dance neighborhoods" (magnetic domains) where everyone is synchronized The "dance style" spreads from one dancer to the next - this propagation is the exchange interaction. Some dance floors (crystal structures) naturally encourage everyone to dance the same way, creating strong magnets." using DALL-E 3 from OpenAI.
Generated image from "A stadium filled with people, each holding a flashlight. In a magnet, something special happens - everyone agrees to point their flashlights in the same direction. Suddenly, that side of the stadium becomes brilliantly bright. This coordinated alignment is what creates a magnet's strength. Each flashlight is like an electron's magnetic moment, and when aligned, they create a powerful cumulative effect." using DALL-E 3 from OpenAI.
Generated image from "Imagine a stadium filled with people, each holding a flashlight. In normal materials, people are pointing their flashlights in random directions, so the overall stadium appears dim from above because the light is scattered in all directions." using DALL-E 3 from OpenAI.
This paper presents MatterGen, a model that generates stable, diverse inorganic materials across the periodic table and can further be fine-tuned to steer the generation towards a broad range of property constraints. To enable this, the authors introduce a new diffusion-based generative process that produces crystalline structures by gradually refining atom types, coordinates, and the periodic lattice.
This paper introduces LLaDA, a diffusion model trained from scratch under the pre-training and supervised finetuning (SFT) paradigm. LLaDA models distributions through a forward data masking process and a reverse process, parameterized by a vanilla Transformer to predict masked tokens. https://arxiv.org/abs/2502.09992
Domains registered within days of this post. Not a dataset - just a wordlist
Here we showcase a few key latent features and their relationships to each other, points colored by their Tc. We animate from 0 K to ~130 K.
Superconductor candidates sampled at a target Tc of 130k
Generated image from "A hairy frog" using DALL-E 3 from OpenAI.
Generated model from an image using the StabilityAI API.
Generated image from "A marble sculpture of a human male with white background" using the StabilityAI API.