Straight-Line Diffusion Model for Efficient 3D Molecular Generation

Diffusion-based models have shown great promise in molecular generation but often require a large number of sampling steps to generate valid samples. In this paper, we introduce a novel Straight-Line Diffusion Model (SLDM) to tackle this problem, by formulating the diffusion process to follow a linear trajectory. The proposed process aligns well with the noise sensitivity characteristic of molecular structures and uniformly distributes reconstruction effort across the generative process, thus enhancing learning efficiency and efficacy. Consequently, SLDM achieves state-of-the-art performance on 3D molecule generation benchmarks, delivering a 100-fold improvement in sampling efficiency. Furthermore, experiments on toy data and image generation tasks validate the generality and robustness of SLDM, showcasing its potential across diverse generative modeling domains.

@article{ni2025_2503.02918,
  title={ Straight-Line Diffusion Model for Efficient 3D Molecular Generation },
  author={ Yuyan Ni and Shikun Feng and Haohan Chi and Bowen Zheng and Huan-ang Gao and Wei-Ying Ma and Zhi-Ming Ma and Yanyan Lan },
  journal={arXiv preprint arXiv:2503.02918},
  year={ 2025 }
}