{"ID":2826698,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.18251","arxiv_id":"2512.18251","title":"CrystalFormer-CSP: Thinking Fast and Slow for Crystal Structure Prediction","abstract":"Crystal structure prediction is a fundamental problem in materials science. We present CrystalFormer-CSP, an efficient framework that unifies data-driven heuristic and physics-driven optimization approaches to predict stable crystal structures for given chemical compositions. The approach combines pretrained generative models for space-group-informed structure generation and a universal machine learning force field for energy minimization. Reinforcement fine-tuning can be employed to further boost the accuracy of the framework. We demonstrate the effectiveness of CrystalFormer-CSP on benchmark problems and showcase its usage via web interface and language model integration.","short_abstract":"Crystal structure prediction is a fundamental problem in materials science. We present CrystalFormer-CSP, an efficient framework that unifies data-driven heuristic and physics-driven optimization approaches to predict stable crystal structures for given chemical compositions. The approach combines pretrained generative...","url_abs":"https://arxiv.org/abs/2512.18251","url_pdf":"https://arxiv.org/pdf/2512.18251v1","authors":"[\"Zhendong Cao\",\"Shigang Ou\",\"Lei Wang\"]","published":"2025-12-20T07:22:58Z","proceeding":"cond-mat.mtrl-sci","tasks":"[\"cond-mat.mtrl-sci\",\"cs.LG\",\"physics.comp-ph\"]","methods":"[\"Language Model\"]","has_code":false}