Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materials

TL;DR

Zatom-1 is a versatile multimodal Transformer model that unifies generative and predictive tasks for 3D molecules and materials, enabling scalable pretraining and transfer learning across domains.

Contribution

It introduces a simplified Transformer architecture trained with a multimodal flow matching objective for cross-domain 3D molecular and material modeling.

Findings

Outperforms specialized baselines on generative and predictive benchmarks.

Enables fast, stable sampling with scalable pretraining.

Improves molecular property prediction via transfer from material modeling.

Abstract

General-purpose 3D modeling in chemistry 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, a cross-domain, general-purpose model architecture that unifies generative and predictive learning of 3D molecules and materials. Zatom-1 is a deliberately simplified 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 cross-domain generative pretraining as a universal initialization for downstream multi-task prediction of properties, energies, and forces. Empirically, Zatom-1 outperforms or competes with specialized baselines on both multi-task generative and predictive benchmarks in data-controlled settings, while improving generative inference speed by more than an order of magnitude. Our experiments demonstrate positive predictive transfer between data domains from joint generative pretraining: modeling materials during generative pretraining improves molecular property prediction accuracy. Open-source code and model weights are freely available at https://github.com/Zatom-AI/zatom.