用潜在流技术实现分子生成与优化，兼顾性质目标与结构有效性。
Property-Guided Molecular Generation and Optimization via Latent Flows
- 构建属性组织的潜在空间，结合流匹配生成先验与梯度引导。
- 在固定预算下高效实现多目标优化，支持可控权衡。
- 适合药物设计与分子逆向工程研究者使用。
分子发现正被越来越多地视为逆向设计问题：在可行性约束下寻找满足特定性质谱的分子结构。尽管近年来的生成模型提供了化学空间的连续潜在表示，但在这些表示中进行定向优化常导致有效性下降、结构保真度丢失或行为不稳定。我们提出 MoltenFlow，一个模块化框架，将属性组织的潜在表示与流匹配生成先验及基于梯度的引导相结合。该方法在单一潜在空间框架内支持条件生成与局部优化。我们证明，有引导的潜在流可在固定代理预算下实现高效的多目标分子优化，并支持可控的权衡；同时，学习到的流先验提升了无条件生成质量。
原文摘要 · Abstract (English)
Molecular discovery is increasingly framed as an inverse design problem: identifying molecular structures that satisfy desired property profiles under feasibility constraints. While recent generative models provide continuous latent representations of chemical space, targeted optimization within these representations often leads to degraded validity, loss of structural fidelity, or unstable behavior. We introduce MoltenFlow, a modular framework that combines property-organized latent representations with flow-matching generative priors and gradient-based guidance. This formulation supports both conditioned generation and local optimization within a single latent-space framework. We show that guided latent flows enable efficient multi-objective molecular optimization under fixed oracle budgets with controllable trade-offs, while a learned flow prior improves unconditional generation quality.
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。