Suiren-1.0用3D到2D的压缩框架，实现分子性质精准预测。
Suiren-1.0 Technical Report: A Family of Molecular Foundation Models
- 用7000万样本预训练18亿参数模型，结合空间自监督与SE(3)等变架构
- 在1350万分子间作用数据上持续预训练，提升多体系统建模能力
- 通过扩散蒸馏将复杂结构压缩为2D表示，适合快速下游应用
我们提出Suiren-1.0，一套用于精确建模多样化有机体系的分子基础模型家族。该系列包含三个专用变体：Suiren-Base、Suiren-Dimer和Suiren-ConfAvg，集成于一个连接三维构象几何与二维统计系综空间的算法框架中。首先，使用7000万样本的密度泛函理论数据集对18亿参数的Suiren-Base进行预训练，采用空间自监督与SE(3)-等变架构，在量子性质预测任务中表现稳健。随后，通过1350万分子间相互作用样本对Suiren-Dimer进行持续预训练，扩展其多体系统建模能力。为实现高效下游应用，我们提出基于扩散的构象压缩蒸馏（CCD）框架，将复杂的3D结构表征压缩为2D构象平均表示，从而生成轻量级的Suiren-ConfAvg模型，可从SMILES或分子图生成高保真表示。全面评估表明，Suiren-1.0在多项任务上达到当前最优性能。所有模型与基准测试均已开源。
原文摘要 · Abstract (English)
We introduce Suiren-1.0, a family of molecular foundation models for the accurate modeling of diverse organic systems. Suiren-1.0 comprising three specialized variants (Suiren-Base, Suiren-Dimer, and Suiren-ConfAvg) is integrated within an algorithmic framework that bridges the gap between 3D conformational geometry and 2D statistical ensemble spaces. We first pre-train Suiren-Base (1.8B parameters) on a 70M-sample Density Functional Theory dataset using spatial self-supervision and SE(3)-equivariant architectures, achieving robust performance in quantum property prediction. Suiren-Dimer extends this capability through continued pre-training on 13.5M intermolecular interaction samples. To enable efficient downstream application, we propose Conformation Compression Distillation (CCD), a diffusion-based framework that distills complex 3D structural representations into 2D conformation-averaged representations. This yields the lightweight Suiren-ConfAvg, which generates high-fidelity representations from SMILES or molecular graphs. Our extensive evaluations demonstrate that Suiren-1.0 establishes state-of-the-art results across a range of tasks. All models and benchmarks are open-sourced.
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。