Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation 事件

Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation arXiv:2606.09278v1 Announce Type: cross Abstract: Large Language Models frequently hallucinate in precision-critical domains such as technical diagramming and mechanical design, where outputs must satisfy strict geometric constraints. We study open-ended geometric synthesis from natural language: translating free-form descriptions into precise constructions whose entities must simultaneously satisfy do