{"ID":2854922,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.13055","arxiv_id":"2510.13055","title":"Reciprocal Space Attention for Learning Long-Range Interactions","abstract":"Machine learning interatomic potentials (MLIPs) have revolutionized the modeling of materials and molecules by directly fitting to ab initio data. However, while these models excel at capturing local and semi-local interactions, they often prove insufficient when an explicit and efficient treatment of long-range interactions is required. To address this limitation, we introduce Reciprocal-Space Attention (RSA), a framework designed to capture long-range interactions in the Fourier domain. RSA can be integrated with any existing local or semi-local MLIP framework. The central contribution of this work is the mapping of a linear-scaling attention mechanism into Fourier space, enabling the explicit modeling of long-range interactions such as electrostatics and dispersion without relying on predefined charges or other empirical assumptions. We demonstrate the effectiveness of our method as a long-range correction to the MACE backbone across diverse benchmarks, including dimer binding curves, dispersion-dominated layered phosphorene exfoliation, and the molecular dipole density of bulk water. Our results show that RSA consistently captures long-range physics across a broad range of chemical and materials systems. The code and datasets for this work is available at https://github.com/rfhari/reciprocal_space_attention","short_abstract":"Machine learning interatomic potentials (MLIPs) have revolutionized the modeling of materials and molecules by directly fitting to ab initio data. However, while these models excel at capturing local and semi-local interactions, they often prove insufficient when an explicit and efficient treatment of long-range intera...","url_abs":"https://arxiv.org/abs/2510.13055","url_pdf":"https://arxiv.org/pdf/2510.13055v1","authors":"[\"Hariharan Ramasubramanian\",\"Alvaro Vazquez-Mayagoitia\",\"Ganesh Sivaraman\",\"Atul C. Thakur\"]","published":"2025-10-15T00:35:47Z","proceeding":"cond-mat.mtrl-sci","tasks":"[\"cond-mat.mtrl-sci\",\"cs.LG\",\"physics.chem-ph\",\"physics.comp-ph\"]","methods":"[]","has_code":false,"code_links":[{"ID":608206,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2854922,"paper_url":"https://arxiv.org/abs/2510.13055","paper_title":"Reciprocal Space Attention for Learning Long-Range Interactions","repo_url":"https://github.com/rfhari/reciprocal_space_attention","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}