Suiren-1.0 Technical Report: A Family of Molecular Foundation Models
This work addresses the modeling gap between three-dimensional molecular conformations and two-dimensional statistical representations by introducing the Suiren-1.0 family of molecular foundation models. Built upon an SE(3)-equivariant architecture, Suiren-1.0 integrates spatial self-supervised learning with large-scale pretraining on density functional theory data and features a novel Conformational Compression Distillation (CCD) framework—leveraging diffusion models for the first time to compress 3D structures into efficient 2D representations. The model encompasses monomers, dimers, and conformational ensembles, establishing a multimodal molecular representation system that achieves state-of-the-art performance across multiple molecular property prediction tasks. All models and evaluation benchmarks are publicly released.