{"ID":2896593,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.06853","arxiv_id":"2507.06853","title":"DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models","abstract":"Molecular structure elucidation from spectra is a fundamental challenge in molecular science. Conventional approaches rely heavily on expert interpretation and lack scalability, while retrieval-based machine learning approaches remain constrained by limited reference libraries. Generative models offer a promising alternative, yet most adopt autoregressive architectures that overlook 3D geometry and struggle to integrate diverse spectral modalities. In this work, we present DiffSpectra, a generative framework that formulates molecular structure elucidation as a conditional generation process, directly inferring 2D and 3D molecular structures from multi-modal spectra using diffusion models. Its denoising network is parameterized by the Diffusion Molecule Transformer, an SE(3)-equivariant architecture for geometric modeling, conditioned by SpecFormer, a Transformer-based spectral encoder capturing multi-modal spectral dependencies. Extensive experiments demonstrate that DiffSpectra accurately elucidates molecular structures, achieving 40.76% top-1 and 99.49% top-10 accuracy. Its performance benefits substantially from 3D geometric modeling, SpecFormer pre-training, and multi-modal conditioning. To our knowledge, DiffSpectra is the first framework that unifies multi-modal spectral reasoning and joint 2D/3D generative modeling for de novo molecular structure elucidation.","short_abstract":"Molecular structure elucidation from spectra is a fundamental challenge in molecular science. Conventional approaches rely heavily on expert interpretation and lack scalability, while retrieval-based machine learning approaches remain constrained by limited reference libraries. Generative models offer a promising alter...","url_abs":"https://arxiv.org/abs/2507.06853","url_pdf":"https://arxiv.org/pdf/2507.06853v2","authors":"[\"Liang Wang\",\"Yu Rong\",\"Tingyang Xu\",\"Zhenyi Zhong\",\"Zhiyuan Liu\",\"Pengju Wang\",\"Deli Zhao\",\"Qiang Liu\",\"Shu Wu\",\"Liang Wang\",\"Yang Zhang\"]","published":"2025-07-09T13:57:20Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CE\",\"physics.chem-ph\",\"q-bio.MN\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}