{"ID":2895303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.09785","arxiv_id":"2507.09785","title":"Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow","abstract":"Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we build upon flow-matching and propose two mechanisms for accelerating training and inference of generative models for 3D molecular conformer generation. For fast training, we introduce the SO(3)-Averaged Flow training objective, which leads to faster convergence to better generation quality compared to conditional optimal transport flow or Kabsch-aligned flow. We demonstrate that models trained using SO(3)-Averaged Flow can reach state-of-the-art conformer generation quality. For fast inference, we show that the reflow and distillation methods of flow-based models enable few-steps or even one-step molecular conformer generation with high quality. The training techniques proposed in this work show a path towards highly efficient molecular conformer generation with flow-based models.","short_abstract":"Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we build upon flow-matchin...","url_abs":"https://arxiv.org/abs/2507.09785","url_pdf":"https://arxiv.org/pdf/2507.09785v1","authors":"[\"Zhonglin Cao\",\"Mario Geiger\",\"Allan dos Santos Costa\",\"Danny Reidenbach\",\"Karsten Kreis\",\"Tomas Geffner\",\"Franco Pellegrini\",\"Guoqing Zhou\",\"Emine Kucukbenli\"]","published":"2025-07-13T20:48:21Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"physics.chem-ph\"]","methods":"[\"Diffusion Model\"]","has_code":false}