Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials

Title: Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials
Authors: Morehead, Alex; Cretu, Miruna; Panescu, Antonia; Anand, Rishabh; Weiler, Maurice; Perez, Tynan; Blau, Samuel; Farrell, Steven; Bhimji, Wahid; Jain, Anubhav; Sahasrabuddhe, Hrushikesh; Lio, Pietro; Jaakkola, Tommi; Gomez-Bombarelli, Rafael; Ying, Rex; Erichson, N. Benjamin; Mahoney, Michael W.
Publication Year: 2026
Collection: ArXiv.org (Cornell University Library)
Subject Terms: Machine Learning; Materials Science; Artificial Intelligence
Description: General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities. However, most existing AI approaches are optimized for a single domain (molecules or materials) and a single task (generation or prediction), which limits representation sharing and transfer. We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials. Zatom-1 is a Transformer trained with a multimodal flow matching objective that jointly models discrete atom types and continuous 3D geometries. This approach supports scalable pretraining with predictable gains as model capacity increases, while enabling fast and stable sampling. We use joint generative pretraining as a universal initialization for downstream multi-task prediction of properties, energies, and forces. Empirically, Zatom-1 matches or outperforms specialized baselines on both generative and predictive benchmarks, while reducing the generative inference time by more than an order of magnitude. Our experiments demonstrate positive predictive transfer between chemical domains from joint generative pretraining: modeling materials during pretraining improves molecular property prediction accuracy. Open-source code: https://github.com/Zatom-AI/zatom ; 32 pages, 10 figures, 15 tables. ICLR 2026 FM4Science. Code, data, and model weights are available at https://github.com/Zatom-AI/zatom
Document Type: text
Language: unknown
Relation: http://arxiv.org/abs/2602.22251
Availability: http://arxiv.org/abs/2602.22251
Accession Number: edsbas.EAFCEE0F
Database: BASE