Scalable Autoregressive 3D Molecule Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cheng, Austin H., Sun, Chong, Aspuru-Guzik, Alán
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909777829822464
author Cheng, Austin H.
Sun, Chong
Aspuru-Guzik, Alán
author_facet Cheng, Austin H.
Sun, Chong
Aspuru-Guzik, Alán
contents Generative models of 3D molecular structure play a rapidly growing role in the design and simulation of molecules. Diffusion models currently dominate the space of 3D molecule generation, while autoregressive models have trailed behind. In this work, we present Quetzal, a simple but scalable autoregressive model that builds molecules atom-by-atom in 3D. Treating each molecule as an ordered sequence of atoms, Quetzal combines a causal transformer that predicts the next atom's discrete type with a smaller Diffusion MLP that models the continuous next-position distribution. Compared to existing autoregressive baselines, Quetzal achieves substantial improvements in generation quality and is competitive with the performance of state-of-the-art diffusion models. In addition, by reducing the number of expensive forward passes through a dense transformer, Quetzal enables significantly faster generation speed, as well as exact divergence-based likelihood computation. Finally, without any architectural changes, Quetzal natively handles variable-size tasks like hydrogen decoration and scaffold completion. We hope that our work motivates a perspective on scalability and generality for generative modelling of 3D molecules.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13791
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable Autoregressive 3D Molecule Generation
Cheng, Austin H.
Sun, Chong
Aspuru-Guzik, Alán
Machine Learning
Chemical Physics
Generative models of 3D molecular structure play a rapidly growing role in the design and simulation of molecules. Diffusion models currently dominate the space of 3D molecule generation, while autoregressive models have trailed behind. In this work, we present Quetzal, a simple but scalable autoregressive model that builds molecules atom-by-atom in 3D. Treating each molecule as an ordered sequence of atoms, Quetzal combines a causal transformer that predicts the next atom's discrete type with a smaller Diffusion MLP that models the continuous next-position distribution. Compared to existing autoregressive baselines, Quetzal achieves substantial improvements in generation quality and is competitive with the performance of state-of-the-art diffusion models. In addition, by reducing the number of expensive forward passes through a dense transformer, Quetzal enables significantly faster generation speed, as well as exact divergence-based likelihood computation. Finally, without any architectural changes, Quetzal natively handles variable-size tasks like hydrogen decoration and scaffold completion. We hope that our work motivates a perspective on scalability and generality for generative modelling of 3D molecules.
title Scalable Autoregressive 3D Molecule Generation
topic Machine Learning
Chemical Physics
url https://arxiv.org/abs/2505.13791