Score: 2

Straight-Line Diffusion Model for Efficient 3D Molecular Generation

Published: March 4, 2025 | arXiv ID: 2503.02918v2

By: Yuyan Ni , Shikun Feng , Haohan Chi and more

Potential Business Impact:

Makes computers design new molecules 100 times faster.

Business Areas:
Simulation Software

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.

Country of Origin
🇨🇳 China

Repos / Data Links

Page Count
26 pages

Category
Computer Science:
Machine Learning (CS)