arXiv:2606.14215v1 Announce Type: new 
Abstract: The emergence of Large Language Models (LLMs) has inspired the vision of generating bespoke crystal materials directly from natural-language instructions, enabling users to design materials through intuitive, conversational interaction. Existing text-to-crystal generative models represent important early steps toward this goal, but they suffer from two critical limitations: (i) restricted input formats that require highly structured descriptions (e.g., chemical formulas), and (ii) one-directional generation, where models can map text to crystal but cannot perform the inverse. These limitations prevent fully conversational workflows and hinder alignment with users' inherently ambiguous and evolving desiderata. We address these challenges with LapidaryEngine, the first model to support fully conversational crystal generation. LapidaryEngine accepts free-form natural-language requests and performs iterative refinement and editing in a dialogue-like manner. The key innovation is a pivot representation, a third, intermediate form that enables bidirectional translation between text and crystal structures despite the absence of direct paired datasets. Leveraging this pivot allows robust interpretation of user feedback and precise structural control. We demonstrate LapidaryEngine across diverse tasks, including insulator discovery, stability optimization, compositional modification, and structural editing, showcasing its ability to align generated materials with user intent in an interactive manner.

تم تقديم LapidaryEngine كنموذج مبتكر يمكّن من توليد البلورات بشكل كامل من خلال المحادثة، مما يسمح للمستخدمين بإنشاء مواد بلورية مخصصة من خلال تعليمات باللغة الطبيعية. تعالج هذه الابتكار القيود المفروضة على النماذج الحالية من النص إلى البلورة، والتي تتطلب مدخلات منظمة وتفتقر إلى قدرات التوليد ثنائي الاتجاه.

Se ha presentado el LapidaryEngine como un modelo innovador que permite la generación de cristales de manera completamente conversacional, permitiendo a los usuarios crear materiales cristalinos personalizados a través de instrucciones en lenguaje natural. Esta innovación aborda las limitaciones de los modelos existentes de texto a cristal, que requieren entradas estructuradas y carecen de capacidades de generación bidireccional.

Le LapidaryEngine a été introduit comme un modèle révolutionnaire permettant la génération de cristaux entièrement conversationnelle, permettant aux utilisateurs de créer des matériaux cristallins sur mesure via des instructions en langage naturel. Cette innovation répond aux limitations des modèles existants de texte à cristal, qui nécessitent des entrées structurées et manquent de capacités de génération bidirectionnelle.

The LapidaryEngine has been introduced as a groundbreaking model that enables fully conversational crystal generation, allowing users to create bespoke crystal materials through natural-language instructions. This innovation addresses the limitations of existing text-to-crystal models, which require structured inputs and lack bidirectional generation capabilities.