解决分子生成中潜在空间暗区问题，提升生成稳定性与化学有效性。
Smoothing Dark Areas in Molecular Latent Diffusion
- 通过拓扑优化的变分自编码器，让解码器内化化学结构约束。
- 在QM9上降低77%的FCD-3D，在GEOM-Drugs上降低52%。
- 无需测试时化学修正，适合零样本骨架补全等任务。
潜在扩散是可扩展3D分子生成的有前景框架，但要求潜在空间在后验样本外仍保持平滑、有效且可导航。现有分子VAE通常基于重建目标学习，无法保证此类潜在空间。我们发现这导致了‘暗区’：扩散采样可达但解码为不连通或化学无效分子的潜在区域。与图像生成不同，分子解码需严格结构与化学精度，微小潜在扰动即可引发灾难性失败。因此我们提出TopVAE，一种拓扑优化的变分自编码器，在训练中使解码器内化结构与化学约束，消除测试时化学修正需求。TopVAE显著提升非后验鲁棒性，搭配标准DiT后，在QM9上实现77%更低的FCD-3D，达到最高V&C，GEOM-Drugs上降低52%的FCD-3D，零样本骨架补全中产生1.29倍更稳定且连通的分子。
原文摘要 · Abstract (English)
Latent diffusion is a promising framework for scalable 3D molecular generation, but it requires a latent space that remains smooth, valid, and navigable beyond posterior samples. Existing molecular VAEs, however, are typically learned through reconstruction-based objectives, which do not guarantee such a latent space. We show that this leads to dark areas: regions of latent space that are reachable during diffusion sampling but decode to disconnected or chemically invalid molecules. Unlike in image generation, molecular decoding requires strict structural and chemical precision, so even small latent perturbations can produce catastrophic failures. We therefore propose TopVAE, a topology-optimized VAE that reduces dark areas by making the decoder internalize structural and chemical constraints during training, eliminating the need for test-time chemical correction. TopVAE greatly improves off-posterior robustness, and when paired with a standard DiT, achieves $77\%$ lower FCD-3D on QM9, the highest V&C, $52\%$ lower FCD-3D on GEOM-Drugs, and $1.29{\times}$ more stable and connected molecules on zero-shot scaffold inpainting.
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。