Tootfinder

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
Jeffri Murrugarra-LLerena, Haoran Niu, K. Suzanne Barber, Hal Daum\'e III, Yang Trista Cao, Paola Cascante-Bonilla
https://arxiv.org/abs/2508.09245

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
As visual assistant systems powered by visual language models (VLMs) become more prevalent, concerns over user privacy have grown, particularly for blind and low vision users who may unknowingly capture personal private information in their images. Existing privacy protection methods rely on coarse-grained segmentation, which uniformly masks entire private objects, often at the cost of usability. In this work, we propose FiGPriv, a fine-grained privacy protection framework that selectively mask…

Beyond the Hype: Mapping Uncertainty and Gratification in AI Assistant Use
Karen Joy, Tawfiq Ammari, Alyssa Sheehan
https://arxiv.org/abs/2506.09220 https:…

Beyond the Hype: Mapping Uncertainty and Gratification in AI Assistant Use
This paper examines the gap between the promises and real-world performance of emerging AI personal assistants. Drawing on interviews with early adopters of devices like Rabbit R1 and Humane AI Pin, as well as services like Ohai and Docus, we map user experiences through the lens of Uses and Gratifications and Uncertainty Reduction Theory. We identify three core types of user uncertainty, functional, interactional, and social, and explore how each disrupts different user gratifications. We show…

Amazon to Acquire AI Device Startup Bee https://ground.news/article/amazon-buys-bee-maker-of-50-wearable-ai-personal-assistant

Neural and Cognitive Impacts of AI: The Influence of Task Subjectivity on Human-LLM Collaboration
Matthew Russell, Aman Shah, Giles Blaney, Judith Amores, Mary Czerwinski, Robert J. K. Jacob
https://arxiv.org/abs/2506.04167

Neural and Cognitive Impacts of AI: The Influence of Task Subjectivity on Human-LLM Collaboration
AI-based interactive assistants are advancing human-augmenting technology, yet their effects on users' mental and physiological states remain under-explored. We address this gap by analyzing how Copilot for Microsoft Word, a LLM-based assistant, impacts users. Using tasks ranging from objective (SAT reading comprehension) to subjective (personal reflection), and with measurements including fNIRS, Empatica E4, NASA-TLX, and questionnaires, we measure Copilot's effects on users. We also evaluate …