Publications

DialogLab provides a unified interface to configure conversational scenes, define agent personas, manage group structures, specify turn-taking rules, and orchestrate transitions between scripted narratives and improvisation.
[DOI]
[pdf]
[30s Preview]
[Video Figure]
[Github]

Leverage multi-view diffusion models and 3D Gaussian Splatting to enhance XR communication and collaboration around objects.
[DOI]
[pdf]
[30s Preview]
[Video Figure]
[Project Page]

ThingMoji is a type of user-captured cut-outs to enhance user expression and foster more effective
communication between streamers and their audience in the comment section
[Preprint]
Leverage instance segmentation approaches to enrich communication centered around objects and elevate real-time collaboration in remote settings.
[Paper]
[30s Preview]
[Video Figure]
[Talk]
[Project Page]
Employ proxemic metaphors within the virtual conversational space to enhance turn-taking dynamics in groups of varying sizes (small to medium-sized groups) with Virtual Floor and Mallable Mirrors.
[Paper]
[30s Preview]
[Video Figure]
[Talk]
[Project Page]
Enhance awareness with in-group and between-group dimensions and flexible boundaries for breakout group conversations.
[Paper]
[30s Preview]
[Video Figure]
[Talk]
[Seminar Talk]
Service
Design and source code from Link |