Research

Researching what intelligence can become.

Our published research and ongoing work across AI, domain specialization and physical intelligence.

IntelligenceAugust 2026Published

Domain-specific intelligence: adapting large language models for specialized professional contexts

We examine how specialized professional knowledge can be incorporated into large language models to produce more accurate, contextually appropriate responses in high-stakes domains including construction, medicine and engineering.

BuildJune 2026Published

Multimodal understanding of technical drawings in the built environment

This paper presents our approach to interpreting architectural and engineering drawings using vision-language models, with findings on accuracy across different document types and drawing conventions.

SystemsMay 2026Published

Context preservation across intelligence transitions in multi-domain AI systems

We explore the problem of maintaining user context as AI systems transition between specialized domains, presenting a framework for coherent multi-domain interactions.

HealthApril 2026Published

Responsible AI in health information: a framework for accurate, appropriately-bounded responses

Health information represents a particularly sensitive application of AI. This paper outlines our approach to accuracy, epistemic humility and appropriate boundary-setting in the Moldulus Health intelligence.

SystemsMarch 2026Preprint

Intelligent environments: embedding AI perception into physical spaces

An early-stage exploration of how AI systems can begin to perceive and respond to physical environments, with initial findings from our lab research program.

FashionFebruary 2026Published

Fashion as structured design space: applying AI to creative development workflows

We present Moldulus Fashion as a case study in applying AI reasoning to creative and material design problems, with an analysis of how structured knowledge about material, construction and form supports the creative process.