UbiWell Lab at UbiComp 2026
Published on
Several UbiWell Lab members will be attending UbiComp/ISWC 2026 in Shanghai! We’re looking forward to a busy week of presenting our research, participating in workshops and the Doctoral Colloquium, leading a hands-on tutorial, and helping organize the Mental Health workshop.
Overview
- 8 IMWUT papers
- 2 workshop papers
- 1 Doctoral Colloquium presentation and poster
- Organizing a tutorial
- Co-organizing the Mental Health workshop
- Members attending: Akshat, Ha, Jiachen, Yuna, Erin, Shreeti, and Samarth.
Papers
Choube et al., IMWUT 2025
Akshat’s paper investigates how researchers currently handle data imputation and reveals that most treat this step as low-priority, defaulting to simple strategies without evaluating their impact on study outcomes.
Le et al., IMWUT 2025
Ha’s paper presents ACAI, a novel context-assisted activity annotation interface that allows participants to efficiently label their daily activities by accepting or adjusting system-generated activity suggestions while explicitly expressing uncertainty about temporal boundaries.
Choube et al., IMWUT 2026
Akshat’s second paper introduces DAIMON, an AI-augmented research dashboard designed to enable new human-AI collaborative workflows for researchers conducting longitudinal sensing studies.
Das Swain et al., IMWUT 2026
Vedant’s paper examines seamful design for human-in-the-loop digital phenotyping of mental health, exploring how users can better understand, evaluate, and influence sensing-based mental health models.
Le et al., IMWUT 2026
Ha’s second paper presents GLOSS4HAR, a multi-agent LLM-based system that combines passive sensing data and participant self-reports to correct activity annotations and support lower-effort activity labeling.
Naito et al., IMWUT 2026
Yuna’s paper introduces a person- and context-aware framework for adaptively selecting filter parameters when estimating pulse rate variability from wearable wrist PPG signals.
Negi et al., IMWUT 2026
Samarth’s paper, Beyond the Binary, introduces PRISM, a framework that moves beyond binary definitions of receptivity by modeling receptivity to digital health interventions as a probabilistic time-to-event distribution.
Negi et al., IMWUT 2026
Samarth’s second paper presents the first systematic evaluation of cross-study generalization for receptivity models, examining whether models can transfer across interventions, populations, and sensing configurations.
Song et al., Mental Health Workshop
Erin will present her paper, Beyond Fine-Tuning: Participant-Specific Model Design for Mental Health Prediction, at the Mental Health workshop. The work explores whether personalization should extend beyond participant-specific training and fine-tuning to the design of the model itself.
Naito et al., WellComp Workshop
Yuna will present her paper, Supporting Couples’ Social Well-being in Daily Life: A Needs Assessment and Co-design with Co-located Couples, at the WellComp workshop. The work explores how ubiquitous sensing and AI might support couples’ relationships in everyday life while preserving authenticity, autonomy, and control.
Doctoral Colloquium
Jiachen will participate in the UbiComp/ISWC 2026 Doctoral Colloquium and present a poster on her ongoing dissertation work, From “What” to “How” and “Why”: Sharing LLM-Generated Retrospective Summaries of Older Adults’ Passive Tracking Data with Remote Family Members.
Her work explores how AI-generated summaries of multimodal sensing data can move beyond reporting what happened to help older adults and their remote family members understand patterns, context, and possible explanations, ultimately supporting communication and care coordination.
Tutorial
Akshat and Ha will co-lead a hands-on tutorial on building multi-agent AI systems for mobile and wearable sensing data. The tutorial will focus on health, behavior, and activity modeling and how researchers can extend multi-agent approaches to their own datasets and sensor streams.
Participants will work with GLOSS, our open-source multi-agent framework for sensing data, and get hands-on experience building and experimenting with multi-agent sensing pipelines.
Workshop
Varun is helping co-organize the 11th Mental Health Sensing and Intervention Workshop, bringing together researchers working at the intersection of ubiquitous computing, sensing, and mental health.