arXiv：cs.LG· Federico Ottomano, Gaopeng Ren, Kim E. Jelfs, Yingzhen Li, Alex M. Ganose·· 5 小时前AI 评分32
KRONOS：面向 3D 分子生成的自回归潜在扩散框架
Autoregressive latent diffusion for 3D molecule generation
AI 导读
KRONOS 是一个潜在自回归扩散框架，在 Unified AutoEncoder（UAE）的潜在空间中生成分子，联合建模分子图拓扑与几何结构，并保留自回归生成在生成过程中确定分子大小的灵活性。
正文
Abstract:Three-dimensional (3D) molecule generation has been dominated by diffusion models, which achieve strong generation quality but typically require molecular size to be specified (or predicted) separately before generation. This can be limiting for fragment-based molecule generation, central to drug discovery, where the size of the generated structure is itself part of the design problem. Autoregressive models determine size during generation and naturally support partial-structure conditioning, but balancing unconditional and fragment-conditioned generation remains challenging. We introduce KRONOS, a latent autoregressive diffusion framework that generates molecules in the latent space of a Unified AutoEncoder (UAE), jointly modeling molecular graph topology and geometry, while retaining the flexibility of autoregressive generation. We further introduce a mixed training strategy inspired by the Fill-in-the-Middle (FIM) paradigm, enabling a single left-to-right autoregressive model to support both unconditional and fragment-conditioned generation. Experiments on QM9 and GEOM-Drugs demonstrate strong unconditional generation performance and competitive fragment-conditioned generation.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.09277 [cs.LG] |
| (or arXiv:2607.09277v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.09277 arXiv-issued DOI via DataCite |
Submission history
From: Federico Ottomano [view email]
[v1]
Fri, 10 Jul 2026 10:47:11 UTC (3,608 KB)
[v2]
Fri, 2 Oct 2026 12:38:15 UTC (3,638 KB)
来源：arXiv：cs.LG · arxiv.org