All

Papers

Browse and search HCI research papers from All

Active Filters

Institution: University of California Los Angeles

22 results

The Shape of My-AI: How Multimodality Shapes Trust and Persuasion in Interactions with an AI-Generated Future Self

AI-generated future selves allow people to engage in dialogue with a personalized digital representation of themselves decades ahead, yet it remains unclear how presentation modality shapes their psychological impact. We report a randomized between-subjects study (n=92) comparing three modalities of an AI-generated fu…

Constanze Albrecht et al.Massachusetts Institute of Technology

Balancing Efficiency and Empathy: Healthcare Providers' Perspectives on AI-Supported Workflows for Serious Illness Conversations in the Emergency Department

Serious Illness Conversations (SICs)—discussions about values and care preferences for patients with life-threatening illness—rarely occur in Emergency Departments (EDs), despite evidence that early conversations improve care alignment and reduce unnecessary interventions. We interviewed 11 ED providers to identify ch…

Menglin Zhao et al.Northeastern University

Beyond Riding: Passenger Engagement with Driver Labor through Gamified Interactions

Modern cities across the globe increasingly rely on ridehail services for on-demand transportation and mobility. But for drivers, such marketed affordances give rise to hidden burdens and vulnerabilities that evade the oversight of consumers and regulators. To effectively advance worker protections and motivate more s…

Jane Hsieh et al.Carnegie Mellon University

DeltaDorsal: Enhancing Hand Pose Estimation with Dorsal Features in Egocentric Views

The proliferation of XR devices has made egocentric hand pose estimation a vital task, yet this perspective is inherently challenged by frequent finger occlusions. To address this, we propose a novel approach that leverages the rich information in dorsal hand skin deformation, unlocked by recent advances in dense visu…

William Huang et al.University of California Los Angeles

AdRecommended

Learn AI Coding at CodeNow

Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work.

Explore Now

Behavioral Indicators of Overreliance During Interaction with Conversational Language Models

LLMs are now embedded in a wide range of everyday scenarios. However, their inherent hallucinations risk hiding misinformation in fluent responses, raising concerns about overreliance on AI. Detecting overreliance is challenging, as it often arises in complex, dynamic contexts and cannot be easily captured by post-hoc…

Chang Liu et al.Tsinghua University

PriorWeaver: Prior Elicitation via Iterative Dataset Construction

In Bayesian analysis, prior elicitation, or the process of facilitating the expression of one’s beliefs to inform statistical modeling, is an essential yet challenging step. Analysts often have beliefs about real-world variables and their relationships. However, existing tools require analysts to translate these belie…

Yuwei Xiao et al.University of California Los Angeles

Flowco: Mixed-Initiative Authoring of Reliable End-to-End Data Analyses via Dataflow Graphs and LLMs

Conducting data analysis typically involves authoring code to trans- form, visualize, analyze, and interpret data. Large Language Models (LLMs) are now capable of generating such code for simple, routine analyses, and they have the potential to democratize data science by enabling those with limited programming expert…

Stephen Freund et al.Williams College

Dreamcrafter: Immersive Editing of 3D Radiance Fields Through Flexible, Generative Inputs and Outputs

Authoring 3D scenes is a central task for spatial computing applications. Competing visions for lowering existing barriers are (1) focus on immersive, direct manipulation of 3D content or (2) leverage AI techniques that capture real scenes (3D Radiance Fields such as, NeRFs, 3D Gaussian Splatting) and modify them at a…

Cyrus Vachha et al.University of California

Beyond Code Generation: LLM-supported Exploration of the Program Design Space

In this work, we explore explicit Large Language Model (LLM)-powered support for the iterative design of computer programs. Program design, like other design activity, is characterized by navigating a space of alternative problem formulations and associated solutions in an iterative fashion. LLMs are potentially power…

J.D. Zamfirescu-Pereira et al.University of California - Berkeley

Proactive Conversational Agents with Inner Thoughts

One of the long-standing aspirations in conversational AI is to allow them to autonomously take initiatives in conversations, i.e. being proactive. This is especially challenging for multi-party conversations. Prior NLP research focused mainly on predicting the next speaker from contexts like preceding conversations.…

Xingyu Bruce Liu et al.University of California Los Angeles

WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users

Existing pose estimation models perform poorly on wheelchair users due to a lack of representation in training data. We present a data synthesis pipeline to address this disparity in data collection and subsequently improve pose estimation performance for wheelchair users. Our configurable pipeline generates synthetic…

William Huang et al.

University of California, Los Angeles

rTisane: Externalizing conceptual models for data analysis increases engagement with domain knowledge and improves statistical model quality

Statistical models should accurately reflect analysts’ domain knowledge about variables and their relationships. While recent tools let analysts express these assumptions and use them to produce a resulting statistical model, it remains unclear what analysts want to express and how externalization impacts statistical…

Eunice Jun et al.University of California Los Angeles

Odyssey: An Interactive Workbench for Expert-Driven Floating-Point Expression Rewriting

In recent years, researchers have proposed a number of automated tools to identify and improve floating-point rounding error in math- ematical expressions. However, users struggle to effectively apply these tools. In this paper, we work with novices, experts, and tool developers to investigate user needs during the ex…

Edward Misback et al.University Of Washington

Rapsai: Accelerating Machine Learning Prototyping of Multimedia Applications through Visual Programming

In recent years, there has been a proliferation of multimedia applications that leverage machine learning (ML) for interactive experiences. Prototyping ML-based applications is, however, still challenging, given complex workflows that are not ideal for design and experimentation. To better understand these challenges,…

Ruofei Du et al.Google

Visual Captions: Augmenting Verbal Communication with On-the-fly Visuals

Video conferencing solutions like Zoom, Google Meet, and Microsoft Teams are becoming increasingly popular for facilitating conversations, and recent advancements such as live captioning help people better understand each other. We believe that the addition of visuals based on the context of conversations could furthe…

Xingyu Bruce Liu et al.University of California Los Angeles

Understanding and Supporting Debugging Workflows in Multiverse Analysis

Multiverse analysis—a paradigm for statistical analysis that considers all combinations of reasonable analysis choices in parallel—promises to improve transparency and reproducibility. Although recent tools help analysts specify multiverse analyses, they remain difficult to use in practice. In this work, we identify d…

Ken Gu et al.University Of Washington

CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding

Authors make their videos visually accessible by adding audio descriptions (AD), and auditorily accessible by adding closed captions (CC). However, creating AD and CC is challenging and tedious, especially for non-professional describers and captioners, due to the difficulty of identifying accessibility problems in…

Xingyu Bruce Liu et al.University of California Los Angeles

Tisane: Authoring Statistical Models via Formal Reasoning from Conceptual and Data Relationships

Proper statistical modeling incorporates domain theory about how concepts relate and details of how data were measured. However, data analysts currently lack tool support for recording and reasoning about domain assumptions, data collection, and modeling choices in an integrated manner, leading to mistakes that can co…

Eunice Jun et al.University of California Los Angeles

Tea: A High-level Language and Runtime System for Automating Statistical Analysis

Though statistical analyses are centered on research questions and hypotheses, current statistical analysis tools are not. Users must first translate their hypotheses into specific statistical tests and then perform API calls with functions and parameters. To do so accurately requires that users have statistical exper…

Eunice Jun et al.University of California Los Angeles

Circadian Rhythms and Physiological Synchrony: Evidence of the Impact of Diversity on Small Group Creativity

Circadian rhythms determine daily sleep cycles, mood, and cognition. Depending on an individual's circadian preference, or chronotype (i.e.,``early birds'' and ``night owls''), the rhythms shift earlier or later in the day. Early birds experience circadian arousal peaks earlier in the morning than night owls. Prior wo…

Eunice Jun et al.University of California Los Angeles

Groups and creativity

Paper Title	Authors	Research Topics
The Shape of My-AI: How Multimodality Shapes Trust and Persuasion in Interactions with an AI-Generated Future Self AI-generated future selves allow people to engage in dialogue with a personalized digital representation of themselves decades ahead, yet it remains unclear how presentation modality shapes their psychological impact. We report a randomized between-subjects study (n=92) comparing three modalities of an AI-generated fu…	CA Constanze Albrecht et al.Massachusetts Institute of Technology
Balancing Efficiency and Empathy: Healthcare Providers' Perspectives on AI-Supported Workflows for Serious Illness Conversations in the Emergency Department Serious Illness Conversations (SICs)—discussions about values and care preferences for patients with life-threatening illness—rarely occur in Emergency Departments (EDs), despite evidence that early conversations improve care alignment and reduce unnecessary interventions. We interviewed 11 ED providers to identify ch…	MZ Menglin Zhao et al.Northeastern University
Beyond Riding: Passenger Engagement with Driver Labor through Gamified Interactions Modern cities across the globe increasingly rely on ridehail services for on-demand transportation and mobility. But for drivers, such marketed affordances give rise to hidden burdens and vulnerabilities that evade the oversight of consumers and regulators. To effectively advance worker protections and motivate more s…	JH Jane Hsieh et al.Carnegie Mellon University
DeltaDorsal: Enhancing Hand Pose Estimation with Dorsal Features in Egocentric Views The proliferation of XR devices has made egocentric hand pose estimation a vital task, yet this perspective is inherently challenged by frequent finger occlusions. To address this, we propose a novel approach that leverages the rich information in dorsal hand skin deformation, unlocked by recent advances in dense visu…	WH William Huang et al.University of California Los Angeles
AdRecommended Learn AI Coding at CodeNow Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work. Explore Now
Behavioral Indicators of Overreliance During Interaction with Conversational Language Models LLMs are now embedded in a wide range of everyday scenarios. However, their inherent hallucinations risk hiding misinformation in fluent responses, raising concerns about overreliance on AI. Detecting overreliance is challenging, as it often arises in complex, dynamic contexts and cannot be easily captured by post-hoc…	CL Chang Liu et al.Tsinghua University
PriorWeaver: Prior Elicitation via Iterative Dataset Construction In Bayesian analysis, prior elicitation, or the process of facilitating the expression of one’s beliefs to inform statistical modeling, is an essential yet challenging step. Analysts often have beliefs about real-world variables and their relationships. However, existing tools require analysts to translate these belie…	YX Yuwei Xiao et al.University of California Los Angeles
Flowco: Mixed-Initiative Authoring of Reliable End-to-End Data Analyses via Dataflow Graphs and LLMs Conducting data analysis typically involves authoring code to trans- form, visualize, analyze, and interpret data. Large Language Models (LLMs) are now capable of generating such code for simple, routine analyses, and they have the potential to democratize data science by enabling those with limited programming expert…	SF Stephen Freund et al.Williams College
Dreamcrafter: Immersive Editing of 3D Radiance Fields Through Flexible, Generative Inputs and Outputs Authoring 3D scenes is a central task for spatial computing applications. Competing visions for lowering existing barriers are (1) focus on immersive, direct manipulation of 3D content or (2) leverage AI techniques that capture real scenes (3D Radiance Fields such as, NeRFs, 3D Gaussian Splatting) and modify them at a…	CV Cyrus Vachha et al.University of California
emoji_events Beyond Code Generation: LLM-supported Exploration of the Program Design Space In this work, we explore explicit Large Language Model (LLM)-powered support for the iterative design of computer programs. Program design, like other design activity, is characterized by navigating a space of alternative problem formulations and associated solutions in an iterative fashion. LLMs are potentially power…	JZ J.D. Zamfirescu-Pereira et al.University of California - Berkeley
Proactive Conversational Agents with Inner Thoughts One of the long-standing aspirations in conversational AI is to allow them to autonomously take initiatives in conversations, i.e. being proactive. This is especially challenging for multi-party conversations. Prior NLP research focused mainly on predicting the next speaker from contexts like preceding conversations.…	XL Xingyu Bruce Liu et al.University of California Los Angeles
WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users Existing pose estimation models perform poorly on wheelchair users due to a lack of representation in training data. We present a data synthesis pipeline to address this disparity in data collection and subsequently improve pose estimation performance for wheelchair users. Our configurable pipeline generates synthetic…	WH William Huang et al.University of California, Los Angeles
emoji_events rTisane: Externalizing conceptual models for data analysis increases engagement with domain knowledge and improves statistical model quality Statistical models should accurately reflect analysts’ domain knowledge about variables and their relationships. While recent tools let analysts express these assumptions and use them to produce a resulting statistical model, it remains unclear what analysts want to express and how externalization impacts statistical…	EJ Eunice Jun et al.University of California Los Angeles
Odyssey: An Interactive Workbench for Expert-Driven Floating-Point Expression Rewriting In recent years, researchers have proposed a number of automated tools to identify and improve floating-point rounding error in math- ematical expressions. However, users struggle to effectively apply these tools. In this paper, we work with novices, experts, and tool developers to investigate user needs during the ex…	EM Edward Misback et al.University Of Washington
emoji_events Rapsai: Accelerating Machine Learning Prototyping of Multimedia Applications through Visual Programming In recent years, there has been a proliferation of multimedia applications that leverage machine learning (ML) for interactive experiences. Prototyping ML-based applications is, however, still challenging, given complex workflows that are not ideal for design and experimentation. To better understand these challenges,…	RD Ruofei Du et al.Google
Visual Captions: Augmenting Verbal Communication with On-the-fly Visuals Video conferencing solutions like Zoom, Google Meet, and Microsoft Teams are becoming increasingly popular for facilitating conversations, and recent advancements such as live captioning help people better understand each other. We believe that the addition of visuals based on the context of conversations could furthe…	XL Xingyu Bruce Liu et al.University of California Los Angeles
Understanding and Supporting Debugging Workflows in Multiverse Analysis Multiverse analysis—a paradigm for statistical analysis that considers all combinations of reasonable analysis choices in parallel—promises to improve transparency and reproducibility. Although recent tools help analysts specify multiverse analyses, they remain difficult to use in practice. In this work, we identify d…	KG Ken Gu et al.University Of Washington
emoji_events CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding Authors make their videos visually accessible by adding audio descriptions (AD), and auditorily accessible by adding closed captions (CC). However, creating AD and CC is challenging and tedious, especially for non-professional describers and captioners, due to the difficulty of identifying accessibility problems in…	XL Xingyu Bruce Liu et al.University of California Los Angeles
emoji_events Tisane: Authoring Statistical Models via Formal Reasoning from Conceptual and Data Relationships Proper statistical modeling incorporates domain theory about how concepts relate and details of how data were measured. However, data analysts currently lack tool support for recording and reasoning about domain assumptions, data collection, and modeling choices in an integrated manner, leading to mistakes that can co…	EJ Eunice Jun et al.University of California Los Angeles
Tea: A High-level Language and Runtime System for Automating Statistical Analysis Though statistical analyses are centered on research questions and hypotheses, current statistical analysis tools are not. Users must first translate their hypotheses into specific statistical tests and then perform API calls with functions and parameters. To do so accurately requires that users have statistical exper…	EJ Eunice Jun et al.University of California Los Angeles
Circadian Rhythms and Physiological Synchrony: Evidence of the Impact of Diversity on Small Group Creativity Circadian rhythms determine daily sleep cycles, mood, and cognition. Depending on an individual's circadian preference, or chronotype (i.e.,``early birds'' and ``night owls''), the rhythms shift earlier or later in the day. Early birds experience circadian arousal peaks earlier in the morning than night owls. Prior wo…	EJ Eunice Jun et al.University of California Los Angeles	Groups and creativity