MEIDNet Prism documentation¶
Learn, build and benchmark multimodal AI for materials discovery. MEIDNet, the reference implementation, learns one latent space shared by crystal structures and their properties, and searches it for materials with the properties you want, using your own data, rules and material families.
The workflow¶
Seven blocks, from a table of known materials to new candidates. Each block is a section of meidnet.yaml, a node in
MEIDNet Studio (where a change in one block updates every block after it) and a section of the
report that each step writes. Click a block to read about it.
From concept to demonstration
The seven blocks at work on the published perovskite model. Click a block to jump to it.
Where to start¶
-
Learn multimodality
What a modality is, the five challenges of multimodal learning, contrastive learning with a playground, and an interactive map of materials modalities.
-
Choose an architecture
Early fusion, late fusion, shared latent spaces, cross-attention and contrastive learning, and an advisor that recommends one for your data and goal.
-
Try MEIDNet
The live Studio runs in the browser without installation;
meidnet demoruns on a laptop CPU. -
Use MEIDNet on my data
A table with an id, property columns and CIFs. Four commands lead from a data check to candidates with reports.
-
Change what it does
Targets, elements, rules and family are set in one YAML file, or with the controls of MEIDNet Studio, which exports the same file.
-
Understand it
How the two modalities are aligned, how the search works, what the reports mean, and where the limits are.
Scope¶
What MEIDNet generates, and what it does not
Generation works for prototype families: a fixed arrangement of sites whose occupants and cell size are chosen (ABX₃ perovskites, A₂BB′X₆ double perovskites, and anything you describe the same way). MEIDNet does not invent new atomic arrangements. Details and roadmap.
Predicted properties are the model's estimates, and the reports say when a prediction is an extrapolation.
Confirm candidates with DFT or experiment; meidnet screen is a first filter.
Paper¶
A. Babu, R. Almeida Gouvêa, P. Vandergheynst, G.-M. Rignanese, MEIDNet: Multimodal generative AI framework for inverse materials design, npj Computational Materials (2026). Citation and benchmarks · code as published (v1.0).
Further reading: A. Babu, R. Almeida Gouvêa, G.-M. Rignanese, Toward automated discovery with generative models multimodal learning and closed loop workflows in inverse materials design, Cell Reports Physical Science 7, 103561 (2026), doi:10.1016/j.xcrp.2026.103561 · A. Babu, N. M. A. Krishnan, Multimodal and cross-modal learning techniques, APL Machine Learning 4, 030901 (2026), doi:10.1063/5.0346744.