EGMOF: Efficient Generation of Metal-Organic Frameworks Using a Hybrid Diffusion- Transformer Architecture

Seunghee Han, Yeonghun Kang, Taeun Bae, Varinia Bernales, Alan Aspuru-Guzik, Jihan Kim

Submission Type: I want my submission to be considered for both oral and poster presentation.

Keywords: Metal-organic Frameworks;Machine learning;Generative Model;

TL;DR: EGMOF is a modular diffusion-transformer framework that generates MOF structures from target properties, delivering high accuracy with little data and avoiding retraining for new properties.

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: 272