用于3D分子生成的自回归潜扩散
Autoregressive latent diffusion for 3D molecule generation
浏览论文内容
中文总结 AI 辅助
研究3D分子生成问题，提出KRONOS潜自回归扩散框架，联合建模分子图拓扑和几何，引入混合训练策略。实验表明其在自回归方法中无条件生成性能领先，与扩散模型竞争，单一架构可支持两种生成范式。
中文摘要 AI 辅助
三维（3D）分子生成一直由扩散模型主导，其生成质量高，但通常需要先验指定分子大小。近期自回归方法缩小了性能差距，支持可变长度生成和基于部分分子上下文的条件生成。然而，平衡无条件和上下文条件生成仍具挑战。我们引入KRONOS，一个在预训练自动编码器的潜空间中生成分子的潜自回归扩散框架，联合建模分子图拓扑和几何结构，同时保留自回归生成的灵活性。我们还引入了受中间填充（FIM）范式启发的混合训练策略，在单个从左到右的自回归模型中实现无条件和片段条件分子生成。在QM9和GEOM - Drugs上的实验表明，KRONOS在自回归方法中实现了领先的无条件生成性能，与扩散模型竞争。此外，片段条件生成对无条件生成性能影响可忽略不计，证明单一架构可支持两种生成范式。
英文摘要
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.
