Generative Inverse Design of Cold Metals for Low-Power Electronics

2026-03-14

AI Summary

Traditional high-throughput screening is constrained by reliance on known compound libraries, hindering the efficient discovery of cold metals with near-Fermi-level band gaps (50–500 meV). This work proposes MatterGPT, a conditional autoregressive Transformer model leveraging symmetry-invariant, invertible SLICES crystal string representations, which enables— for the first time—generative inverse design of cold metals, thereby overcoming database dependency and substantially expanding the explorable chemical space. Through high-throughput DFT validation combined with phonon spectrum and work function calculations, 257 novel cold metals absent from the Materials Project database were identified among 148,506 generated structures. All exhibit thermodynamic and kinetic stability, along with work functions suitable for electronic device contacts.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Metareasoning and Metaheuristics
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Cold metals are a class of metals with an intrinsic energy gap located close to the Fermi level, which enables cold-carrier injection for steep-slope transistors and is therefore promising for low-power electronic applications. High-throughput screening has revealed 252 three-dimensional (3D) cold metals in the Materials Project database, but database searches are inherently limited to known compounds. Here we present an inverse-design workflow that generates 3D cold metals using MatterGPT, a conditional autoregressive Transformer trained on SLICES, an invertible and symmetry-invariant crystal string representation. We curate a training set of 26,309 metallic structures labeled with energy above hull and a unified band-edge distance descriptor that merges p-type and n-type cold-metal characteristics to address severe label imbalance. Property-conditioned generation targeting thermodynamic stability and 50-500 meV band-edge distances produces 148,506 unique candidates; 92.1% are successfully reconstructed to 3D structures and down-selected by symmetry, uniqueness and novelty filters, followed by high-throughput DFT validation. We identify 257 cold metals verified as novel with respect to the Materials Project database, with gaps around the Fermi level spanning 50-500 meV. First-principles phonon, electronic-structure, and work-function calculations for representative candidates confirm dynamical stability and contact-relevant work functions. Our results demonstrate that SLICES-enabled generative transformers can expand the chemical space of cold metals beyond high-throughput screening, providing a route to low-power electronic materials discovery.

Problem

• cold metals
• inverse design
• low-power electronics
• band-edge distance
• materials discovery

Innovation

• inverse design
• generative transformer
• cold metals
• SLICES representation
• low-power electronics