An Autoregressive Approach For Material Generation

Niklas Dobberstein

Submission Type: I want my submission to be considered for poster only

Keywords: Material Discovery, Transformers, Generation, Machine Learning

TL;DR: We present an autoregressive transformer which treats the crystal structure as a sequence by quantizing the unit cell, enabling fast training and inference while also achieving high structural accuracy.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 191