The study of how humans interact with computers and how to design more usable computing interfaces.
Researchers from Tsinghua University and other institutions have developed a new technique called MindShift to tackle problematic smartphone use. This approach leverages large language models to automatically generate persuasive content,…
Continue readingThe research investigates the placebo effect in Human-AI interaction. It shows that even if participants were informed that an AI would decrease their performance, they still performed better when they…
Continue readingThe paper presents the Toloka Visual Question Answering, a crowdsourced dataset designed to test machine learning systems’ performance in grounding visual question answering tasks. These tasks involve drawing a bounding…
Continue readingDecaf is a novel method that can track human hands interacting with faces in 3D from single monocular RGB videos. The method models hands as articulated objects inducing non-rigid face…
Continue readingThe paper examines the use of Large Language Models (LLMs) like GPT-3 and GPT-4 in content moderation roles. It evaluates their performance in rule-based community moderation and toxic content detection….
Continue readingThe paper explores a new method of authentication for smart voice assistants, such as Alexa, Google Home, Siri, etc., called AirBone authentication. This method aims to counter voice spoofing attacks,…
Continue readingThis research paper, published by Marcel Claus, Frouke Hermens, and Stefano Bromuri, discusses a user study of visualisations of spatio-temporal eye tracking data. The study compares four different visualization techniques…
Continue readingThis research paper provides insights into how children (aged 7-13) value and design AI interfaces, specifically teachable machines. The study involved a co-design session where children and adults participated in…
Continue readingThe paper introduces ALLURE, a protocol for systematically auditing and improving the accuracy of text evaluation by Large Language Models (LLMs) using iterative In-Context-Learning (ICL). ALLURE audits the evaluation of…
Continue readingThe research addresses the potential threat posed by Large Language Models (LLMs) such as ChatGPT, which can be exploited to generate misinformation. The study examines whether LLM-generated misinformation is more…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
