Emotional empathy, the ability to understand and respond to others' emotions, is essential for effective communication. We propose Empathy-GPT, featuring embodied conversational agents with empathic capacity. To a...
详细信息
ISBN:
(纸本)9798400707186
Emotional empathy, the ability to understand and respond to others' emotions, is essential for effective communication. We propose Empathy-GPT, featuring embodied conversational agents with empathic capacity. To address the limitations of rule-based conversational agents, we leverage contextual understanding and adaptation capabilities of large language models (LLMs) to coordinate multiple modalities (e.g., agent's tone, body movements, and facial expressions). To enhance user engagement in human-agent communication, agents dynamically respond to users' voices and facial expressions, providing contextually empathic responses.
While it may initially seem counterintuitive to view degradation within an operating system as advantageous, one could argue that, when intentionally designed, the controlled breakdown of materials-whether physical, c...
详细信息
ISBN:
(纸本)9798400707186
While it may initially seem counterintuitive to view degradation within an operating system as advantageous, one could argue that, when intentionally designed, the controlled breakdown of materials-whether physical, chemical, or biological-can be leveraged for specific functions. To apply this principle to the development of functional morphing devices, we have introduced the concept of "Degrade to Function" (DtF) [16]. This concept is aimed at creating eco-friendly and self-contained morphing devices that operate through a series of environmentally-triggered degradations. In this demonstration, we elucidate the DtF design strategy and present five application examples across a range of ecosystems.
We present an initial step towards building a system for programmers to edit code using free-form sketch annotations drawn directly onto editor and output windows. Using a working prototype system as a technical probe...
详细信息
ISBN:
(纸本)9798400707186
We present an initial step towards building a system for programmers to edit code using free-form sketch annotations drawn directly onto editor and output windows. Using a working prototype system as a technical probe, an exploratory study (N = 6) examines how programmers sketch to annotate Python code to communicate edits for an AI model to perform. The results reveal personalized workflow strategies and how similar annotations vary in abstractness and intention across different scenarios and users.
Physically assistive robots present an opportunity to significantly increase the well-being and independence of individuals with motor impairments or other forms of disability who are unable to complete activities of ...
详细信息
ISBN:
(纸本)9798400707186
Physically assistive robots present an opportunity to significantly increase the well-being and independence of individuals with motor impairments or other forms of disability who are unable to complete activities of daily living (ADLs). Speech interfaces, especially ones that utilize Large Language Models (LLMs), can enable individuals to effectively and naturally communicate high-level commands and nuanced preferences to robots. In this work, we demonstrate an LLM-based speech interface for a commercially available assistive feeding robot. Our system is based on an iteratively designed framework, from the paper "VoicePilot: Harnessing LLMs as Speech interfaces for Physically Assistive Robots," that incorporates human-centric elements for integrating LLMs as interfaces for robots. It has been evaluated through a user study with 11 older adults at an independent living facility. Videos are located on our project website(1)
Playing music is a deeply fulflling and universally cherished activity, yet the steep learning curve often discourages novice amateurs. Traditional music creation demands significant time and effort to master musical ...
详细信息
ISBN:
(纸本)9798400707186
Playing music is a deeply fulflling and universally cherished activity, yet the steep learning curve often discourages novice amateurs. Traditional music creation demands significant time and effort to master musical theory, instrumental mechanics, motor skills, and notation reading. To lower these barriers, innovative technology-driven approaches are necessary. This proposal introduces CrAIzy MIDI, an AI-powered wearable musical instrument designed to simplify and enhance the music-playing experience for beginners. CrAIzy MIDI integrates three key technologies: wearable userinterfaces, AI-generated music, and multi-modality tools. The wearable interface allows users to play multiple instruments using intuitive finger and palm movements, reducing the complexity of traditional instruments. AI-generated music segments enable users to input a few pitches and have the AI complete the musical piece, aiding beginners in overcoming composition challenges. The multi-modality experience enhances engagement by allowing adjustments in music effects through visual stimuli such as light color and intensity changes. Together, these features make music creation more accessible and enjoyable, fostering continuous practice and exploration for novice musicians.
As users engage more frequently with AI conversational agents, conversations may exceed their "memory" capacity, leading to failures in correctly leveraging certain memories for tailored responses. However, ...
详细信息
ISBN:
(纸本)9798400706288
As users engage more frequently with AI conversational agents, conversations may exceed their "memory" capacity, leading to failures in correctly leveraging certain memories for tailored responses. However, in finding past memories that can be reused or referenced, users need to retrieve relevant information in various conversations and articulate to the AI their intention to reuse these memories. To support this process, we introduce Memolet, an interactive object that reifies memory reuse. users can directly manipulate Memolet to specify which memories to reuse and how to use them. We developed a system demonstrating Memolet's interaction across various memory reuse stages, including memory extraction, organization, prompt articulation, and generation refinement. We examine the system's usefulness with an N=12 within-subject study and provide design implications for future systems that support user-AI conversational memory reusing.
Embodying avatars in virtual reality (VR) has transformed human experiences, such as in medicine and education. However, there is limited information about users' self-identifications and perceptions of highly fan...
详细信息
ISBN:
(纸本)9798400707186
Embodying avatars in virtual reality (VR) has transformed human experiences, such as in medicine and education. However, there is limited information about users' self-identifications and perceptions of highly fantastical avatars. This pilot study explored the impact of avatar types of low and high fantasy levels on adults' perceptions and behaviors. Participants (N = 18) engaged in a VR experience with either a human or blue Muppet avatar to complete body movement tasks, a cube-touching game, and free-form exploration. Findings showed that participants in the high fantasy avatar condition reported higher identification with their avatar and more interest in social-emotional activities relative to the low fantasy human avatar condition. Across both conditions, participants stood extremely close to the virtual mirror. Additionally, we report on participants preferences and priorities for their future avatars. This offers insights for future research on avatar design, with implications for more engaging VR experience.
Existing visual assistive technologies are built for simple and common use cases, and have few avenues for blind people to customize their functionalities. Drawing from prior work on DIY assistive technology, this pap...
详细信息
ISBN:
(纸本)9798400706288
Existing visual assistive technologies are built for simple and common use cases, and have few avenues for blind people to customize their functionalities. Drawing from prior work on DIY assistive technology, this paper investigates end-user programming as a means for users to create and customize visual access programs to meet their unique needs. We introduce ProgramAlly, a system for creating custom filters for visual information, e.g., 'find NUMBER on BUS', leveraging three end-user programming approaches: block programming, natural language, and programming by example. To implement ProgramAlly, we designed a representation of visual filtering tasks based on scenarios encountered by blind people, and integrated a set of on-device and cloud models for generating and running these programs. In user studies with 12 blind adults, we found that participants preferred different programming modalities depending on the task, and envisioned using visual access programs to address unique accessibility challenges that are otherwise difficult with existing applications. Through ProgramAlly, we present an exploration of how blind end-users can create visual access programs to customize and control their experiences.
We demonstrate FlowRing, a ring-form-factor input device that enables interaction across a range of ad-hoc surfaces including desks, pants, palms and fngertips with seamless switching between them. This versatility su...
详细信息
ISBN:
(纸本)9798400707186
We demonstrate FlowRing, a ring-form-factor input device that enables interaction across a range of ad-hoc surfaces including desks, pants, palms and fngertips with seamless switching between them. This versatility supports systems that require both high precision as well as mobile control, such as mobile XR. FlowRing consists of a miniature optical fow sensor, skin-contact microphone, and IMU, providing a unique ergonomic design that rests at the base of the fnger like conventional jewelry. We show the potential of FlowRing to enable precise control of interfaces on available surfaces via music player application and whiteboarding application.
The proceedings contain 95 papers. The topics discussed include: Idyll Studio: a structured editor for authoring interactive & data-driven articles;LipNotif: use of lips as a non-contact tactile notification inter...
ISBN:
(纸本)9781450386357
The proceedings contain 95 papers. The topics discussed include: Idyll Studio: a structured editor for authoring interactive & data-driven articles;LipNotif: use of lips as a non-contact tactile notification interface based on ultrasonic tactile presentation;SensiCut: material-aware laser cutting using speckle sensing and deep learning;Marcelle: composing interactive machine learning workflows and interfaces;false positives vs. false negatives: the effects of recovery time and cognitive costs on input error preference;KondoCloud: improving information management in cloud storage via recommendations based on file similarity;ModularHMD: SoundsRide: a reconfigurable mobile head-mounted display enabling ad-hoc peripheral interactions with the real world;and affordance-synchronized music mixing for in-car audio augmented reality.
暂无评论