TY - GEN
T1 - Memento
T2 - 2026 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2026
AU - Kim, Yoonsang
AU - Yang, Yalong
AU - Kaufman, Arie E.
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - We introduce Memento, a conversational AR assistant that permanently captures and memorizes users' verbal queries alongside their spatiotemporal and activity contexts. By storing these 'memories,' Memento discovers connections between users' recurring interests and the contexts that trigger them. Upon detection of similar or identical spatiotemporal activity, Memento proactively recalls user interests and delivers up-to-date responses through AR, seamlessly integrating the AR experience into their daily routine. Unlike prior work, each interaction in Memento is not a transient event, but part of a connected series of interactions with coherent long-term perspective, tailored to the user's broader multimodal (visual, spatial, temporal, and embodied) context. We conduct a preliminary evaluation through user feedback from participants of diverse expertise in immersive apps, and explore the value of a proactive contextaware AR assistant in everyday settings. We share our findings and challenges in designing a proactive, context-aware AR system.
AB - We introduce Memento, a conversational AR assistant that permanently captures and memorizes users' verbal queries alongside their spatiotemporal and activity contexts. By storing these 'memories,' Memento discovers connections between users' recurring interests and the contexts that trigger them. Upon detection of similar or identical spatiotemporal activity, Memento proactively recalls user interests and delivers up-to-date responses through AR, seamlessly integrating the AR experience into their daily routine. Unlike prior work, each interaction in Memento is not a transient event, but part of a connected series of interactions with coherent long-term perspective, tailored to the user's broader multimodal (visual, spatial, temporal, and embodied) context. We conduct a preliminary evaluation through user feedback from participants of diverse expertise in immersive apps, and explore the value of a proactive contextaware AR assistant in everyday settings. We share our findings and challenges in designing a proactive, context-aware AR system.
KW - Augmented Reality
KW - Context-aware
KW - Large Language Models
KW - Personal Assistant
KW - Proactive Visualization
KW - Spatial Computing
KW - Wearable AI
UR - https://www.scopus.com/pages/publications/105038729308
U2 - 10.1109/VRW70859.2026.00180
DO - 10.1109/VRW70859.2026.00180
M3 - Conference contribution
AN - SCOPUS:105038729308
T3 - Proceedings - 2026 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2026
SP - 993
EP - 1000
BT - Proceedings - 2026 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2026
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 21 March 2026 through 25 March 2026
ER -