用流匹配优化分子构象生成，提升质量并减少采样步骤。
Flow-Matching Based Refiner for Molecular Conformer Generation
- 从上游模型输出初始化采样，重调度噪声水平跳过低信噪比阶段。
- 在GEOM-QM9和GEOM-Drugs上以更少步数提升构象质量。
- 适合需要高质量分子构象的药物发现研究者使用。
低能量分子构象生成（MCG）是药物发现中的基础性难题。基于去噪的方法，如扩散模型和流匹配模型，通过学习从简单先验分布到分子构象分布的映射来生成构象。然而，这些方法在采样过程中常因误差累积而表现不佳，尤其是在低信噪比（SNR）阶段，该阶段训练困难。为此，本文提出一种面向MCG任务的流匹配精修器。该方法从上游去噪模型生成的混合质量输出开始采样，并重新调度噪声尺度，从而跳过低信噪比阶段，有效提升样本质量。在GEOM-QM9和GEOM-Drugs基准数据集上，生成器-精修器流水线在减少总去噪步骤的同时，显著提升了构象质量，同时保持了良好的多样性。
原文摘要 · Abstract (English)
Low-energy molecular conformers generation (MCG) is a foundational yet challenging problem in drug discovery. Denoising-based methods include diffusion and flow-matching methods that learn mappings from a simple base distribution to the molecular conformer distribution. However, these approaches often suffer from error accumulation during sampling, especially in the low SNR steps, which are hard to train. To address these challenges, we propose a flow-matching refiner for the MCG task. The proposed method initializes sampling from mixed-quality outputs produced by upstream denoising models and reschedules the noise scale to bypass the low-SNR phase, thereby improving sample quality. On the GEOM-QM9 and GEOM-Drugs benchmark datasets, the generator-refiner pipeline improves quality with fewer total denoising steps while preserving diversity.
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。