70 research outputs found
CreativeConnect: Supporting Reference Recombination for Graphic Design Ideation with Generative AI
No full textGraphic designers often get inspiration through the recombination of references. Our formative study (N=6) reveals that graphic designers focus on conceptual keywords during this process, and want support for discovering the keywords, expanding them, and exploring diverse recombination options of them, while still having room for designers' creativity. We propose CreativeConnect, a system with generative AI pipelines that helps users discover useful elements from the reference image using keywords, recommends relevant keywords, generates diverse recombination options with user-selected keywords, and shows recombinations as sketches with text descriptions. Our user study (N=16) showed that CreativeConnect helped users discover keywords from the reference and generate multiple ideas based on them, ultimately helping users produce more design ideas with higher self-reported creativity, compared to the baseline system without generative pipelines. While CreativeConnect was shown effective in ideation, we discussed how CreativeConnect can be extended to support other types of tasks in creativity support. © 2024 Copyright held by the owner/author(s
A Context-Aware Onboarding Agent for Metaverse Powered by Large Language Models
No full textOne common asset of metaverse is that users can freely explore places and actions without linear procedures. Thus, it is hard yet important to understand the divergent challenges each user faces when onboarding metaverse. Our formative study (N = 16) shows that frst-time users ask questions about metaverse that concern 1) a short-term spatiotemporal context, regarding the user’s current location, recent conversation, and actions, and 2) a long-term exploration context regarding the user’s experience history. Based on the fndings, we present PICAN, a Large Language Model-based pipeline that generates context-aware answers to users when onboarding metaverse. An ablation study (N = 20) reveals that PICAN’s usage of context made responses more useful and immersive than those generated without contexts. Furthermore, a user study (N = 21) shows that the use of long-term exploration context promotes users’ learning about the locations and activities within the virtual environment
Recommended from our members
Pneumatics powered by liquid nitrogen for robotics applications
No full textDespite its potential as a high efficiency power-actuation mechanism, cryogen powered pneumatics system have been one of the least popular choice for robotic engineers due to its nonlinearities and other modeling complexities. For this thesis, an ideal model of liquid nitrogen powered pressurized vessel for pneumatic muscle actuator application with minimal complexity has initially been developed. Few control algorithms have been tested to investigate the robustness of the pneumatic force generation in creating stable profiles of output pressure of pressurized vessel. Then finally, a more realistic, low-cost, portable, increased-safety solution, both in terms of physical size and control platform, has been provided to meet the practical needs in the field of advanced robotics
Feed-O-Meter: Investigating AI-generated mentee personas as interactive agents for scaffolding design feedback practice
No full textEffective feedback, including critique and evaluation, helps designers develop design concepts and refine their ideas, supporting informed decision-making throughout the iterative design process. However, in studio-based design courses, students often struggle to provide feedback due to a lack of confidence and fear of being judged, which limits their ability to develop essential feedback-giving skills. Recent advances in large language models (LLMs) suggest that role-playing with AI agents can allow learners to engage in multi-turn feedback without the anxiety of external judgment or the time constraints of real-world settings. Yet prior studies have raised concerns that LLMs struggle to behave like real people in role-play scenarios, diminishing the educational benefits of these interactions. Therefore, designing AI-based agents that effectively support learners in practicing and developing intellectual reasoning skills requires more than merely assigning the target persona’s personality and role to the agent. By addressing these issues, we present Feed-O-Meter, a novel system that employs carefully designed LLM-based agents to create an environment in which students can practice giving design feedback. The system enables users to role-play as mentors, providing feedback to an AI mentee and allowing them to reflect on how that feedback impacts the AI mentee’s idea development process. A user study (N=24) indicated that Feed-O-Meter increased participants’ engagement and motivation through role-switching and helped them adjust feedback to be more comprehensible for an AI mentee. Based on these findings, we discuss future directions for designing systems to foster feedback skills in design education.
Recommended from our members
Examining augmented reality in middle schools through a review of studies on augmented reality in education
No full textAlthough augmented reality (AR) is considered a promising technology in the field of education, many educators are still having trouble distinguishing between AR and virtual reality. Therefore, this report aims to present and refine the understanding of AR technology in middle school-level education based on existing studies published in the last three years. A total of eighteen academic journal articles were reviewed to obtain a comprehensive view of the definitions, types, features, advantages, limitations, and integration methods of AR in middle schools. According to Azuma (1997), AR is a technology that enhances one’s sense of reality by enabling the coexistence and simultaneous interaction of digital information and the real world. The most commonly used types of AR today are marker/vision-based and location-based. Based on the reviewed studies, eight features, five advantages, and six limitations of AR technology are identified. In addition, the ways in which AR technology has been integrated into middle school classrooms are described.Curriculum and Instructio
Synthèse d’hétérocycles azotés complexes par la chimie organométallique du titane
No full textCe projet vise à développer une extension ambitieuse de nos travaux antérieurs sur les thioamides. À partir de substrats bien choisis, il est attendu que des intermédiaires iminium métallés seront générés, après une étape élémentaire de cyclisation. Notre objectif est de démontrer que ce processus peut conduire à des composés hautement fonctionnalisés, résultant de la formation de deux nouvelles liaisons carbone-carbone, réalisées en une seule étape. Les aspects de diastéréosélectivité et d'énantiosélectivité seront étudiés et tous les nouveaux produits hétérocycliques seront inclus dans la chimiothèque nationale pour des tests d'activité biologique.This project aims at developing an ambitious extension of our earlier work on thioamides. From well-chosen substrates, we are expecting to generate cyclised metallated iminium intermediates. Our goal is to demonstrate that this process can lead to highly functionalised compounds, resulting from the formation of two new carbon-carbon bonds, made in a single step. Diastereoselectivity and enantioselectivity aspects will be investigated, and all the new heterocyclic products will be included in the national chemical library for biological tests
Titanium-mediated expedient synthesis of complex nitrogen heterocycles
No full textInternational audienc
Titanium-mediated expedient synthesis of complex nitrogen heterocycles
No full textInternational audienc
Emotional labor among team members: do employees follow emotional display norms for teams, not for customers?
No full textEmotional labor is typically conceptualized as a process in which individuals regulate their emotions in response to display rules. Most research on emotional labor has focused on the influence of display rules at individual-level perceptions but is rarely examined at the team level. We examine the influence of the shared display rules in teams as emotional display norms. This study considers emotional dissonance as the difference between the positive emotional display norm at the team level and positive emotion at the individual level. To examine the purpose of this study, data were collected from leader-follower pairs within teams and based on a three-wave design. Thus, this study conducted a multi-level polynomial regression analysis and used the response surface methodology to interpret the incongruence effect. The results show that the incongruence effect of emotional dissonance is positively related to surface acting. In addition, the moderating effect of regulatory focus significantly strengthens the positive relationship between emotional dissonance and emotion regulation strategies. The results also show that surface acting strategy is negatively related to selfless Organizational citizenship behaviors (OCB). These findings highlight that emotional display norms play an important role as the standard for emotional experience in teams, and especially with the moderating effect of self-regulatory focus, emotion regulation strategies affect the selfless OCB rating of observers
- …
