Actionable Repair via Multimodal AI
What if damage were a prompt: what stories and repair strategies might it generate? This workshop invites participants to work with an AI-supported workflow in which a VLM, accessed through a mobile interface, translates heterogeneous data into spatial models and procedural representations of possible repair interventions. Rather than prescribing a single solution, these proposals make different repair strategies and successive intervention steps explicit and open to comparison and debate.
Working through concrete examples including doors, windows, and a damaged pillar from a larger architectural use case, participants will examine how different repair decisions respond to feasibility, care, and future use. The workshop highlights how AI can support the analysis of existing structures and the development of repair designs, while human expertise remains essential to interpretation and judgment. The workshop is a collaboration with the ETH Chair of Construction Heritage and Preservation, whose team will contribute domain expertise in preservation, material practices, and repair methodologies.
Tutors
Tizian Rein (TU Munich, Munich, Germany)
Tizian Rein is an architect and researcher bridging computational design and building preservation. During his Master‘s studies, he gained research experience in robotics at TU Munich and ETH Zurich. He is currently a doctoral researcher at the Professorship of Digital Fabrication within the Munich Institute for Robotics and Machine Intelligence (MIRMI) and MIT, USA.
Laurence Crouzet (ETH Zurich, Switzerland)
Laurence Crouzet is an architect and a doctoral candidate at ETH Zurich’s Institute for Preservation and Construction History and Institute of Technology in Architecture. Her research focuses on the repair and care of born-digital architecture and related data. She gained her research and teaching experience at McGill, UC Berkeley, UBC, and Université de Montréal.
Adrian Pöllinger (ETH Zurich, Switzerland)
Adrian Pöllinger is a trained architect and postdoctoral researcher supervising the SNSF-funded Digital Construction Archive project at ETH Zurich. His research focuses on data ontologies and curation strategies for the construction data of digitally fabricated architecture. His team will contribute to the discourse on repair through perspectives on data, archiving, and preservation.
Begüm Saral (TU Munich, Munich, Germany)
Begüm Saral is an architect and researcher specializing in mobile robotics and AI for construction and deconstruction. A graduate of ITU and TUM, she is currently a PhD candidate at TUM GNI. Her research within the "SPAICR" project focuses on spatial AI for robotic material reclamation and reuse.
Wen-Shan Cui (ETH Zurich, Switzerland)
Wen-Shan Cui is an architect with a background in architectural visualization and studied at TUM and TU Vienna. She is currently a doctoral researcher at ETH Zurich’s Chair of Construction Heritage and Preservation. Her work within the Digital Construction Archive examines the documentation, monitoring, maintenance, and long-term preservation of robotically fabricated architecture.