IJHCI 2025SweeperBot is a system designed to help screen reader users explore and compare 3D models by answering visual questions. It combines smart viewpoint selection with AI models to generate detailed, accessible descriptions. Studies with blind, low-vision, and sighted participants show it is both feasible and effective.
TOCHI 2024MemoVis is a text editor interface that assists feedback providers in creating reference images with generative AI driven by the feedback comments
UIST 2023PaperToPlace is a novel workflow comprising an authoring pipeline, which allows the authors to rapidly transform and spatialize existing paper instructions into an MR experience, and a consumption pipeline, which computationally places each instruction step at an optimal location that is easy to read and does not occlude key interaction areas.