{"ID":2824823,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.22597","arxiv_id":"2512.22597","title":"Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery","abstract":"Exploring molecular energy landscapes and identifying ground-state conformations are central challenges in computational chemistry. However, generating diverse low-energy conformers from molecular graphs remains expensive with traditional physics-based pipelines. Existing learning-based approaches remain fragmented: generative models capture conformational diversity but often lack reliable energy calibration, whereas deterministic predictors focus on a single structure and fail to represent ensemble variability. Here we introduce EnFlow, to our knowledge, the first energy-guided generative framework that couples flow-based conformer generation with explicit energy landscape modeling for joint conformational ensemble generation and ground-state identification. By integrating generative dynamics with a learned energy model, EnFlow guides sampling toward low-energy regions of the conformational landscape, improving structural fidelity under extremely few sampling steps while enabling energy-based ranking of generated conformations. Experiments on GEOM-QM9 and GEOM-Drugs show that EnFlow achieves strong performance in conformer generation and ground-state identification while requiring only 1--2 ODE sampling steps. Single-point GFN2-xTB evaluations further show that the learned energy scores preserve physically meaningful energetic rankings of generated conformations. These results support explicit energy landscape modeling as an effective strategy for low-energy molecular structure discovery through joint modeling of conformational ensembles and their associated energies.","short_abstract":"Exploring molecular energy landscapes and identifying ground-state conformations are central challenges in computational chemistry. However, generating diverse low-energy conformers from molecular graphs remains expensive with traditional physics-based pipelines. Existing learning-based approaches remain fragmented: ge...","url_abs":"https://arxiv.org/abs/2512.22597","url_pdf":"https://arxiv.org/pdf/2512.22597v2","authors":"[\"Guikun Xu\",\"Xiaohan Yi\",\"Ziqiao Meng\",\"Peilin Zhao\",\"Yatao Bian\"]","published":"2025-12-27T14:00:22Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"physics.chem-ph\"]","methods":"[]","has_code":false}