用快速生成分子，同时保证质量与多样性。
MolSnap: Snap-Fast Molecular Generation with Latent Variational Mean Flow
- 引入因果感知的Transformer，联合编码分子与文本指令。
- 提出变分均值流，单步生成且新颖度达74.5%、多样性70.3%。
- 适合需高效生成高质量分子的药物研发人员使用。
基于文本描述的分子生成是计算化学与药物发现中的基础任务。现有方法常难以兼顾生成质量、多样性与推理速度。本文提出一种因果感知框架，包含两项创新：一是引入因果感知Transformer（CAT），在生成过程中强制因果依赖，联合编码分子图标记与文本指令；二是设计变分均值流（VMF）框架，将隐空间建模为高斯混合分布，增强表达能力，超越单峰先验。VMF实现单步推理，保持优异生成质量与多样性。在四个标准分子基准上实验表明，本模型优于现有最优方法，新颖度最高达74.5%，多样性最高达70.3%，所有数据集有效性均为100%。此外，条件生成仅需1次函数求值（NFE），无条件生成最多5次NFE，显著优于扩散模型的计算效率。
原文摘要 · Abstract (English)
Molecular generation conditioned on textual descriptions is a fundamental task in computational chemistry and drug discovery. Existing methods often struggle to simultaneously ensure high-quality, diverse generation and fast inference. In this work, we propose a novel causality-aware framework that addresses these challenges through two key innovations. First, we introduce a Causality-Aware Transformer (CAT) that jointly encodes molecular graph tokens and text instructions while enforcing causal dependencies during generation. Second, we develop a Variational Mean Flow (VMF) framework that generalizes existing flow-based methods by modeling the latent space as a mixture of Gaussians, enhancing expressiveness beyond unimodal priors. VMF enables efficient one-step inference while maintaining strong generation quality and diversity. Extensive experiments on four standard molecular benchmarks demonstrate that our model outperforms state-of-the-art baselines, achieving higher novelty (up to 74.5\%), diversity (up to 70.3\%), and 100\% validity across all datasets. Moreover, VMF requires only one number of function evaluation (NFE) during conditional generation and up to five NFEs for unconditional generation, offering substantial computational efficiency over diffusion-based methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。