Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.21942 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910171723202560 |
|---|---|
| author | An, Junyi Lu, Xinyu Shi, Yun-Fei Xu, Li-Cheng Zhang, Nannan Qu, Chao Qi, Yuan Cao, Fenglei |
| author_facet | An, Junyi Lu, Xinyu Shi, Yun-Fei Xu, Li-Cheng Zhang, Nannan Qu, Chao Qi, Yuan Cao, Fenglei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21942 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Suiren-1.0 Technical Report: A Family of Molecular Foundation Models An, Junyi Lu, Xinyu Shi, Yun-Fei Xu, Li-Cheng Zhang, Nannan Qu, Chao Qi, Yuan Cao, Fenglei Chemical Physics Artificial Intelligence 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. |
| title | Suiren-1.0 Technical Report: A Family of Molecular Foundation Models |
| topic | Chemical Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2603.21942 |