Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Zhonglin Cao, Mario Geiger, Allan Dos Santos Costa, Danny Reidenbach, Karsten Kreis, Tomas Geffner, Franco Pellegrini, Guoqing Zhou, Emine Kucukbenli
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6522-6542, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-cao25b, title = {Efficient Molecular Conformer Generation with {SO}(3)-Averaged Flow Matching and Reflow}, author = {Cao, Zhonglin and Geiger, Mario and Costa, Allan Dos Santos and Reidenbach, Danny and Kreis, Karsten and Geffner, Tomas and Pellegrini, Franco and Zhou, Guoqing and Kucukbenli, Emine}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {6522--6542}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/cao25b/cao25b.pdf}, url = {https://proceedings.mlr.press/v267/cao25b.html}, 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.} }
Endnote
%0 Conference Paper %T Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow %A Zhonglin Cao %A Mario Geiger %A Allan Dos Santos Costa %A Danny Reidenbach %A Karsten Kreis %A Tomas Geffner %A Franco Pellegrini %A Guoqing Zhou %A Emine Kucukbenli %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-cao25b %I PMLR %P 6522--6542 %U https://proceedings.mlr.press/v267/cao25b.html %V 267 %X 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.
APA
Cao, Z., Geiger, M., Costa, A.D.S., Reidenbach, D., Kreis, K., Geffner, T., Pellegrini, F., Zhou, G. & Kucukbenli, E.. (2025). Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:6522-6542 Available from https://proceedings.mlr.press/v267/cao25b.html.

Related Material