arXiv subjects

Can Liu

Publications and source records attributed to Can Liu.

At least 19 recordsLinked to original sources

arXiv2026

Health Inquiry with AI: How Empathetic Expression and Conversational Contexts Shape Users' Communicative Acts

As online health information-seeking shifts to conversational AI, high-quality information retrieval increasingly relies on users' ``communicative acts''(proactively sharing and seeking information)---similar to how effective diagnosis and personalized guidance are elicited in patient-clinician communication. Drawing on health communication research, this study examines how a chatbot's modality of empathetic expression (Verbal, Visual, Multimodal) and the conversational context (General, Sensitive, Mental Health) influence these acts through a 2 x 2 x 3 within-subjects experiment (N = 48). The results revealed that while verbal and multimodal empathy significantly increased reply length, communicative acts were largely shaped by conversational context, with Sensitive context triggering more question-asking and Mental Health context leading to heightened concerns, assertive responses, and unprompted information disclosure. Combined with qualitative findings, we discuss design implications for building context-sensitive AI health inquiry systems that can encourage active user participation.

cs.HC↗

arXiv2026

Reference-Based Manipulation: A Framework and Pipeline for Multimodal Spatial Reasoning

When manipulating objects in immersive platforms through speech and gesture, users naturally construct spatial references, referring to scene entities, their bodies, or the environment. Leveraging spatial cognition theories, this work systematically examines how users construct and communicate spatial intent. Using a custom toolkit, we conducted a Wizard-of-Oz study to observe unconstrained multimodal (speech + gesture) input patterns in Virtual Reality for scene construction. Based on these findings, we formalize a framework that decomposes spatial references into three core components: Source, Anchor, and Frame, while characterizing their compositional strategies and explicitness. We demonstrate the utility of this Reference-based Manipulation framework by implementing an LLM-based pipeline featuring a set of example interaction techniques with a preliminary technical evaluation. Finally, we discuss key lessons learned for supporting reference-based spatial interaction.

cs.HC↗

arXiv2026

ManyFold: A Design Exploration of Data Visualization on Foldable Mobile Devices

With this work, we explore the unique potential of data visualization on novel foldable mobile devices (foldables). Even though foldables are already commercially available, there is limited knowledge of how to leverage their distinct characteristics for visualization. This gap will only grow as their form factors become increasingly diverse. To address this, we use a two-step approach. First, we present a device-centered design space, structured around physical and usage properties of foldable devices. Second, we introduce a conceptual framework that investigates visualization on foldables from four complementary perspectives: More Displays - distributing multiple views to leverage additional display space; More Shapes - mapping visualizations to spatial fold states; More Interactions - coupling visualization tasks and folding interactions; and More States - enabling responsive visualization through folding. We complement the design space and conceptual framework with a low-fidelity ideation workshop and the subsequent prototyping of interactive artifacts. We reflect on the results and lessons learned from our exploratory, design-driven process and discuss opportunities and challenges, including the gap between our proposed concepts and commercially available foldable devices. By providing conceptual foundations and illustrating the potential of foldables, we hope to inspire and inform the development of future visualization applications for this evolving class of devices.

cs.HC↗

arXiv2026

ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk

Cryptocurrency markets are vulnerable to trade-based manipulation, such as wash trading, which can distort price signals and mislead investors. Prior research has mainly focused on detecting manipulation using fixed rules or labeled examples, offering limited flexibility and interpretability for assessing potential risks. Existing visual analytics tools can reveal basic manipulation-related signals, such as token distribution, but still require substantial manual effort to integrate holder relationships, suspicious behaviors, and market dynamics for risk assessment. To address these limitations, we propose ManiScope, an LLM-assisted visual analytics system for analyzing trade-based manipulation risks in cryptocurrency markets. ManiScope provides coordinated views of token distributions, holder relationships, detailed holder behaviors, price dynamics, and suspicious trading patterns. To further enhance user analysis, ManiScope introduces a human-LLM collaborative visual analytics framework. Rather than acting as a basic reactive LLM assistant, the framework positions the LLM as a co-analyst that infers users' analytical intent and emerging hypotheses from interaction context and surfaces relevant visual, statistical, and synthesized evidence for hypothesis evaluation. This design reduces repetitive inspection and strengthens evidence-based reasoning. We evaluate ManiScope through two case studies and a user study with 12 experienced cryptocurrency practitioners. The results suggest that ManiScope supports effective risk assessment of manipulation, reduces manual effort in evidence-seeking, and organizes findings around user hypotheses.

cs.HC↗

arXiv2026

Vibe Coding for Visualization Implementation: An Empirical Study of Practices and Challenges

Data visualization is essential for data analysis and communication, yet creating expressive visualizations remains labor-intensive. Recent AI-driven ``vibe coding'' tools enable users to generate visualizations through natural language interaction, lowering the barrier to entry. However, visualization implementation requires precise alignment between user intent and visual representation, which may differ from general software development practices. We present an empirical study with 16 participants of varying expertise to examine how users employ vibe coding tools for visualization implementation. Participants completed two visualization tasks and a semi-structured interview. Our findings characterize the diverse practices users adopt across prompting, evaluation, and iteration, and surface the challenges they encounter throughout the process.

cs.HC↗

arXiv2026

MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration

Knowledge workers face increasing challenges in synthesizing information from multiple documents into structured conceptual understanding. This process is inherently iterative: users explore content, identify relationships between concepts, and continuously reorganize their mental models. However, current approaches offer limited support. LLM-based systems let users query information but not shape how knowledge is organized; manual tools like mind maps support structure creation but lack intelligent assistance. This leaves an open opportunity: supporting collaborative construction where users and AI jointly develop an evolving knowledge representation. We present MindTrellis, an interactive visual system where users and AI collaboratively build a dynamic knowledge graph. Users can query the graph to retrieve document-grounded information, and contribute by introducing new concepts, modifying relationships, and reorganizing the hierarchy to reflect their developing understanding. In a user study where 12 participants created slide decks, MindTrellis outperformed retrieval-only baselines in knowledge organization and cognitive load, as measured by expert ratings of content coverage and structural quality.

cs.HC↗

arXiv2026

Proteus: Shapeshifting Desktop Visualizations for Mobile via Multi-level Intelligent Adaptation

With the rise of mobile-first consumption, users increasingly engage with data visualizations on mobile devices. However, the vast majority of existing visualizations are originally authored for desktop environments. Due to significant differences in viewport size and interaction paradigms, directly scaling desktop charts often results in illegible text, information loss, and interaction failures. To bridge this gap, we propose an automated framework to adapt desktop-based visualizations for mobile screens. By systematically categorizing the operations involved in the adaptation process, we establish a multi-level design space. This space defines evolution rules spanning from the global topology level, through the reference frame level, down to the visual elements level. Guided by this theoretical framework, we developed Proteus, a large language model-driven multi-agent system that automatically parses online visualizations, predicts optimal transformation strategies within the design space, and generates equivalent, highly readable visualizations for mobile devices. Case studies and an in-depth user study with 12 participants demonstrate the effectiveness and usability of Proteus.

cs.HC↗

arXiv2026

ReVis: Towards Reusable Image-Based Visualizations with MLLMs

Many expressive visualizations are shared online only as bitmap images, making them difficult to redesign or adapt to new data. Reusing such image-based visualizations requires substantial expertise and is often time-consuming, even for experienced visualization practitioners. Existing work on reproducing visualizations often relies on structured SVG or specifications, supports limited visualization types, and offers limited flexibility for customization. To address these challenges, we present ReVis, a human-AI collaboration approach that enables flexible reuse of image-based visualizations. First, a generic Domain-Specific language (DSL) is proposed to model complex visualizations and support both visualization decomposition and reproduction. Then, ReVis employs an MLLM-based pipeline to parse an image-based visualization into the DSL, delineating its core visual structures and data-to-encoding mappings, and further reproduces the visualization from the DSL. Finally, ReVis includes an interactive interface to allow users to upload visualization images, inspect reproduced results, update the underlying data, and customize visual encodings. A gallery of 40 visualizations demonstrates the expressiveness of the DSL, and a quantitative study evaluates the reproduction quality of ReVis on these examples. Two usage scenarios and user interviews with 16 visualization practitioners demonstrate the effectiveness of ReVis.

cs.HC↗

arXiv2026

Accessible Fine-grained Data Representation via Spatial Audio

Pitch-based sonification of quantitative data increases the accessibility of data visualizations that are otherwise inaccessible for blind and low-vision (BLV) individuals. We argue that, although pitch representations can reveal the coarse-grained information of data, such as data trend and value comparison, they cannot effectively convey the fine-grained details like the sign and exact value of individual data points. Informed by existing sound perception research, we propose a spatial audio-based approach by representing data values as the sound direction in the azimuth plane to achieve accessible fine-grained data representation. We conducted a user study with 26 participants (including 10 BLV participants) on four data perception tasks. The results show our approach significantly outperforms pitch representation on fine-grained data perception tasks like recognizing data signs and exact values, and performs similarly on data trend identification, despite its inferior accuracy on data value comparison.

cs.HC↗

arXiv2026

Orality: A Semantic Canvas for Externalizing and Clarifying Thoughts with Speech

People speak aloud to externalize thoughts as one way to help clarify and organize them. Although Speech-to-text can capture these thoughts, transcripts can be difficult to read and make sense due to disfluencies, repetitions and potential disorganization. To support thinking through verbalization, we introduce Orality, which extracts key information from spoken content, performs semantic analysis through LLMs to form a node-link diagram in an interactive canvas. Instead of reading and working with transcripts, users could manipulate clusters of nodes and give verbal instructions to re-extract and organize the content in other ways. It also provides AI-generated inspirational questions and detection of logical conflicts. We conducted a lab study with twelve participants comparing Orality against speech interaction with ChatGPT. We found that Orality can better support users in clarifying and developing their thoughts. The findings also identified the affordances of both graphical and conversational thought clarification tools and derived design implications.

cs.HC↗

arXiv2026

Stability Anchors and Risk Amplifiers: Tail Spillovers Across Stablecoin Designs

This paper investigates systemic risk transmission across stablecoin markets using Quantile Vector Autoregression (QVAR). Analyzing eight major stablecoins with day data coverage from 2021 to 2025, supplemented by minute-level event studies on three additional coins experiencing major depegs until 2025, we document three findings. First, stabilization mechanism dictates tail-risk behavior: fiat-backed stablecoins function as "stability anchors" with near-zero net spillovers across quantiles, while algorithmic and crypto-collateralized designs become risk amplifiers specifically under extreme market conditions. Second, the theoretical risk isolation between fiat and crypto markets breaks down during stress: direct volatility channels emerge between the US Dollar Index and Bitcoin that bypass stablecoin intermediation. Third, Forbes-Rigobon contagion tests across four depeg events show heterogeneous transmission: after adjusting for volatility, algorithmic stablecoins exhibit significant residual contagion while fiat-backed coins show flight-to-quality effects. These findings imply that uniform stablecoin regulation is inappropriate; regulatory capital buffers for extreme losses should be 2--3x higher for non-fiat-backed stablecoins than median-based measures indicate.

econ.GN↗

arXiv2026

InterFlow: Designing Unobtrusive AI to Empower Interviewers in Semi-Structured Interviews

Semi-structured interviews are a common method in qualitative research. However, conducting high-quality interviews is cognitively demanding and requires strong interviewing skills. To lower this bar, we propose InterFlow, an AI-powered visual scaffold that helps interviewers manage the interview flow and facilitates real-time data sensemaking. The system dynamically adapts the interview script to the ongoing conversation and provides a visual timer to track interview progress and conversational balance. It further supports information capture with three levels of automation: manual entry, AI-assisted summary with user-specified focus, and a co-interview agent that proactively surfaces potential follow-up points. A within-subject user study ($N=12$) indicates that InterFlow reduces interviewers' cognitive load and facilitates the interview process. Based on the user study findings, we provide design implications for unobtrusive and agency-preserving AI assistance under time-sensitive and cognitively-demanding situations.

cs.HC↗

arXiv2026

From Static to Interactive: Authoring Interactive Visualizations via Natural Language

Interactivity is crucial for effective data visualizations. However, it is often challenging to implement interactions for existing static visualizations, since the underlying code and data for existing static visualizations are often not available, and it also takes significant time and effort to enable interactions for them even if the original code and data are available. To fill this gap, we propose Athanor, a novel approach to transform existing static visualizations into interactive ones using multimodal large language models (MLLMs) and natural language instructions. Our approach introduces three key innovations: (1) an action-modification interaction design space that maps visualization interactions into user actions and corresponding adjustments, (2) a multi-agent requirement analyzer that translates natural language instructions into an actionable operational space, and (3) a visualization abstraction transformer that converts static visualizations into flexible and interactive representations regardless of their underlying implementation. Athanor allows users to effortlessly author interactions through natural language instructions, eliminating the need for programming. We conducted two case studies and in-depth interviews with target users to evaluate our approach. The results demonstrate the effectiveness and usability of our approach in allowing users to conveniently enable flexible interactions for static visualizations.

cs.HC↗

arXiv2025

Bunch-by-Bunch Prediction of Beam Transverse Position, Phase, and Length in a Storage Ring Using Neural Networks

Real-time, bunch-by-bunch monitoring of transverse position, longitudinal phase, and bunch length is crucial for beam control in diffraction-limited storage rings, where complex collective dynamics pose unprecedented diagnostic challenges. This study presents a neural network framework that simultaneously predicts these parameters directly from beam position monitor waveforms. The hybrid architecture integrates specialized Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Long Short-Term Memory with Attention (LSTM-Attention) sub-networks, overcoming key limitations of traditional methods such as serial processing chains and batch-mode operation. Validated on experimental data from the Shanghai Synchrotron Radiation Facility and Hefei Light Source, the model achieves high prediction accuracy with a sub-millisecond latency of 0.042 ms per bunch. This performance demonstrates its potential as a core tool for real-time, multi-parameter diagnostics and active feedback in next-generation light sources.

physics.acc-ph↗

arXiv2025

Design Exploration of AI-assisted Personal Affective Physicalization

Personal Affective Physicalization is the process by which individuals express emotions through tangible forms to record, reflect on, and communicate. Yet such physical data representations can be challenging to design due to the abstract nature of emotions. Given the shown potential of AI in detecting emotion and assisting design, we explore opportunities in AI-assisted design of personal affective physicalization using a Research-through-Design method. We developed PhEmotion, a tool for embedding LLM-extracted emotion values from human-AI conversations into parametric design of physical artifacts. A lab study was conducted with 14 participants creating these artifacts based on their personal emotions, with and without AI support. We observed nuances and variations in participants' creative strategies, meaning-making processes and their perceptions of AI support in this context. We found key tensions in AI-human co-creation that provide a nuanced agenda for future research in AI-assisted personal affective physicalization.

cs.HC↗

arXiv2025

\textit{Ab initio} studies of influence of periodic-direction electric fields on spin lifetime and spin diffusion length and the validation of an \textit{ab initio} matrix-drift-diffusion model

Recently, we developed an \textit{ab initio} approach of spin lifetime (\tau_{s}) and spin diffusion length (l_{s}) in solids [Phys. Rev. Lett. 135, 046705 (2025)], based on a density-matrix master equation with quantum treatment of electron scattering processes. In this work, we extend the method to include the drift term due to an electric field along a periodic direction, implemented using a Wannier-representation-based covariant derivative. We employ this approach to investigate the electric-field effect on \tau_{s} and l_{s} of monolayer WSe_{2}, bulk GaAs, bulk GaN, and graphene-h-BN heterostructure. We find that an electric field reduces \tau_{s} of GaAs, due to the induced D'yakonov-Perel'-type spin relaxation. In GaN and graphene-h-BN, \tau_{s} is significantly affected, partly because the electric field generates an effective magnetic field corresponding to the k-derivative of Rashba spin-orbit (magnetic) field. Our results show that l_{s} can be significantly enhanced or suppressed by a moderate downstream or upstream field respectively. While the standard drift-diffusion model performs well for WSe_{2}, it can introduce large errors of the electric-field-induced changes of l_{s} in GaAs, GaN and graphene-h-BN. Our proposed \textit{ab initio} matrix-drift-diffusion model improves results for GaAs and GaN, but still fails for graphene-h-BN. Thus, to accurately capture the influence of electric fields on l_{s} in realistic materials, it is necessary to go beyond the drift-diffusion model and adopt a microscopic \textit{ab initio} methodology. Moreover, in graphene-h-BN, we find that the field-induced changes of \tau_{s} and l_{s} are not only governed by the drift term in the master equation, but are also significantly affected by the electric-field modification of the equilibrium density matrix away from Fermi-Dirac distribution function.

cond-mat.mtrl-sci↗

arXiv2025

GlyphWeaver: Unlocking Glyph Design Creativity with Uniform Glyph DSL and AI

Expressive glyph visualizations provide a powerful and versatile means to represent complex multivariate data through compact visual encodings, but creating custom glyphs remains challenging due to the gap between design creativity and technical implementation. We present GlyphWeaver, a novel interactive system to enable an easy creation of expressive glyph visualizations. Our system comprises three key components: a glyph domain-specific language (GDSL), a GDSL operation management mechanism, and a multimodal interaction interface. The GDSL is a hierarchical container model, where each container is independent and composable, providing a rigorous yet practical foundation for complex glyph visualizations. The operation management mechanism restricts modifications of the GDSL to atomic operations, making it accessible without requiring direct coding. The multimodal interaction interface enables direct manipulation, natural language commands, and parameter adjustments. A multimodal large language model acts as a translator, converting these inputs into GDSL operations. GlyphWeaver significantly lowers the barrier for designers, who often do not have extensive programming skills, to create sophisticated glyph visualizations.

cs.HC↗

arXiv2025

EchoLadder: Progressive AI-Assisted Design of Immersive VR Scenes

Mixed reality platforms allow users to create virtual environments, yet novice users struggle with both ideation and execution in spatial design. While existing AI models can automatically generate scenes based on user prompts, the lack of interactive control limits users' ability to iteratively steer the output. In this paper, we present EchoLadder, a novel human-AI collaboration pipeline that leverages large vision-language model (LVLM) to support interactive scene modification in virtual reality. EchoLadder accepts users' verbal instructions at varied levels of abstraction and spatial specificity, generates concrete design suggestions throughout a progressive design process. The suggestions can be automatically applied, regenerated and retracted by users' toggle control.Our ablation study showed effectiveness of our pipeline components. Our user study found that, compared to baseline without showing suggestions, EchoLadder better supports user creativity in spatial design. It also contributes insights on users' progressive design strategies under AI assistance, providing design implications for future systems.

cs.HC↗