SEARCH · Searcharxiv

Search Searcharxiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17Linked to original sources

arXiv2026

RegulAR: Graph-Grounded Error Recognition and Assistance for Procedural Tasks in AR

Errors are inevitable in procedural tasks, yet most AR guidance systems focus on step-by-step instruction delivery rather than helping users recognize and recover from mistakes. We present RegulAR, an AR task assistant for procedural error recognition and recovery. RegulAR models task instructions as a hierarchical dependency graph and combines this structure with a Multimodal Large Language Model (MLLM) to interpret egocentric observations during execution. This enables RegulAR to track progress, identify deviations by error type, estimate their impact on later steps, and deliver appropriately salient interventions through an in-situ head-up display that visualizes task state and recovery guidance. By making procedural structure explicit, RegulAR supports not only next-step guidance, but also reasoning about what went wrong, why it matters, and how users can get back on track. In a within-subject study (N=12), participants reported better task-structure understanding and recovery support with RegulAR than the MLLM-only baseline.

cs.HC↗

arXiv2026

One Residual with Three Reuses: A Wristband Front End for Gesture Sensing

Continuous wrist-worn hand sensing for gesture interfaces and motor symptom monitoring needs an always-on front end that fits inside a coin-cell power budget while pairing a micro-electro-mechanical-systems (MEMS) inertial measurement unit (IMU) with a 60 GHz frequency-modulated continuous-wave (FMCW) radar to stay robust under occlusion and on-body drift. We present a design study of such a wristband front end in which classifier wake-up gating, mmWave versus IMU routing, and innovation-based EKF measurement reweighting share a single on-chip residual generator. The shared generator occupies 14.4 KB of program memory and 278 B of state and runs at 110K multiply-accumulates (MACs) per frame on an Ambiq Apollo4 Blue Plus class edge microcontroller unit (MCU). Across four public sensor data corpora (IPN Hand, SHREC 2021, MiliPoint 60 GHz FMCW radar, EAT-Radar) the front end reaches detection probability $P_D = 0.72/0.80$ at a 1% false-alarm rate, sustains a 47% classifier invocation energy reduction at 90% gesture detection recall, and lowers pose tracking root-mean-square error by $4.6\times$ under measurement bias drift relative to an adaptive Kalman with $R$-inflation baseline. Measured silicon power and on-body capture are deferred to follow-on hardware; the contribution here is a design study.

cs.LG↗

arXiv2026

D3D-GEN: Robot-Aware Domain-Grounded Interactive 3D World Generation for Social Robotics

Training and validation of Embodied AI for social navigation critically depends on realistic simulation environments, yet many current approaches fail to find a balance between realism and simulability. We propose D3D-GEN, a novel world generation system that combines a domain agent with a retrieval-augmented generation (RAG) pipeline grounded in that domain. Our system enables users to rapidly generate domain-grounded, fully interactive 3D worlds by automating both the collection of domain knowledge and the synthesis of realistic floorplans and object placements, without dependence on any fixed 3D model database. Given a domain description prompt, the research agent collects publicly accessible domain-specific data and constructs a persistent domain database. Using this database, our RAG pipeline generates plausible floorplans and object placements by dynamically querying a user-provided semantic database, which can be easily extended or modified. The output is a fully interactive 3D world loadable by the popular simulators Isaac Sim and Gazebo. With our approach, we have built databases for several common domains (indoor residential, hospital, office) and generated dozens of distinct, plausible simulation environments for each domain. We present D3D-GEN with a local web frontend that facilitates rapid, interactive world generation for robot simulation.

cs.RO↗

arXiv2026

From Sensor Data to Classroom Inquiry: GenAI-Supported Exploration of School Digital Twin Data

Digital Twins for educational buildings can support sustainability-oriented learning, but their use in schools remains limited. This paper presents a GenAI-based chatbot built on top of an existing Digital Twin for two school buildings in Greece, using real IoT data from environmental sensors and energy meters. The chatbot enables educators to query live and historical building data, compare spaces, and generate ideas for classroom activities through natural language. The system was evaluated in an 80-minute workshop with 17 secondary-school educators, who compared it with an existing web-based dashboard. Results show strong perceived usability and pedagogical value, particularly for inquiry-based learning, hypothesis formation, and interdisciplinary lesson planning. Participants also highlighted limitations related to response speed, data verification, trust, and the continued value of visual dashboards. Overall, the findings suggest that GenAI interfaces can make Digital Twin data more accessible for educational use, provided they are designed with transparency, verification, and pedagogical grounding.

cs.HC↗

arXiv2026

From GenAI Virtual Patient Dialogue Logs to Teacher-Interpretable Process Evidence: A Learning Analytics Study in Higher Education

Medical history taking is a dialogue-based clinical reasoning task in which learners must gather, organise, and integrate patient information while the consultation unfolds. Generative AI-powered virtual patients (GenAI VPs) make repeated history taking practice scalable and preserve full turn by turn dialogue. However, these logs are educationally difficult to use directly. Complete transcripts are too detailed for routine teacher review, whereas final scores obscure whether learners followed up patient cues, checked uncertainty, or used summaries to guide later questioning. This study examined whether coded GenAI VP dialogues can provide teacher-interpretable process evidence of clinical reasoning. We analysed 1{,}030 GenAI VP dialogues from 210 second-year medical learners across five weeks chest-pain cases. Each consultation was teacher-scored using a rubric assessing the full history taking dialogue, and consultations were classified within each week as high- or low-rated using the weekly median score. To explain how rated performance was reflected in the dialogue process, we applied three analytic layers to the same coded dialogue data: behavioural prevalence, local co-occurrence using Epistemic Network Analysis, and sequential transition using Transition Network Analysis. High-rated consultations involved more history taking activity, but differences were not simply about volume. High rated consultations more often connected information gathering and symptom exploration with communication, checking, organisation, and synthesis. Summarising and organising moves more often led to verification or mechanism-oriented follow-up. These findings show how layered analysis of GenAI VP dialogue logs can reveal process patterns associated with high rated history taking and support process-focused feedback in medical education.

cs.CL↗

arXiv2026

AniMaster: From Story Texts to Animated Videos via Cinematic Script Generation and Interactive Authoring

Recent advances in Video Generation Models (VGMs) have demonstrated strong capabilities in producing short video clips. However, it is still challenging for everyday creators to leverage these models to produce polished long-form animated videos from brief story texts. Informed by a formative study with both novice creators and film experts, we identify two major challenges of interactive video authoring: (1) the lack of expertise in translating free-form story texts to professional cinematic scripts and finally high-quality animated videos, and (2) the absence of effective ways to convey video design intents to key variables of visual storytelling, such as shot composition, camera controls and shot sequencing. Drawing on narratology and film studies, we propose a three-layer design framework that defines the key design dimensions across three layers (i.e., story texts, cinematic scripts, and animated videos) as well as the translation between them. Built on this framework, we present AniMaster, a VGM-powered authoring tool to enable everyday creators to easily produce smooth animated videos from free-form story texts. AniMaster automatically expands brief story texts to detailed cinematic scripts, and further translates cinematic scripts into polished videos by following professional visual storytelling principles. It also allows users to interactively edit the scripts and refine the generated videos via text instructions and intuitive interactions. We extensively evaluated AniMaster through an in-depth user study with 16 participants, two case studies, and expert interviews with 2 film professionals. The results demonstrate the effectiveness and usability of AniMaster in helping everyday creators create polished animated videos from free-form story texts.

cs.HC↗

arXiv2026

Experts Disagree on How to Fight AI Disinformation, but Agree That Health and Politics Need Different Solutions

When 54 international experts assessed AI-generated disinformation threats, they revealed a surprising pattern: while video deepfakes received the highest average threat ratings in the political domain (M = 6.31/7), the pattern differed in the health domain, where AI-generated text received the highest average rating (M = 5.80). Experts also diverge on what to do: government regulation drew both the most "most effective" (30%) and the most "least effective" (15%) votes, though rating distributions were contested rather than polarized, indicating disagreement over priorities rather than over efficacy. These findings offer an initial expert map of an AI-disinformation landscape that is still rapidly forming.

cs.CY↗

arXiv2026

Collaboratively Eliciting Gestures for Geospatial Data Exploration on an MSE with Tangibles and Styluses

Large tabletop displays and multi-surface environments offer potential for enhancing visual data exploration and collaborative work with geospatial datasets. These systems typically rely on multi-touch interactions, which can pose challenges when the multi-touch sensors misrepresent transitory movements as control inputs, leading to interruptions. Active tangibles and styluses offer an alternative to multi-touch interactions in MSEs, and have shown the potential to facilitate sense-making around large datasets. However, further research is needed to better understand how these modalities can be effectively leveraged for interacting with geospatial data visualizations. To address this, a gesture elicitation study was conducted in which users suggested interactions for 16 geospatial data visualization tasks, presented as a realistic collaborative workflow co-designed with geography and migration researchers. The study produced a taxonomy of user-defined gestures using tangibles and styluses for engaging with geospatial data, along with a thematic analysis of users' experiences with visualization tasks and interaction techniques.

cs.HC↗

arXiv2026

UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering

We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participated in Subtasks 2 (evidence identification), 3 (answer generation), and 4 (answer-evidence alignment). For Subtasks 2 and 3, we propose an answer-first pipeline in which the model generates candidate answers citing specific note sentences before classifying the full evidence set, exploiting the asymmetry between judging relevance in the abstract versus relative to a generated answer. For Subtask 4, we apply self-consistency voting over five independent model calls, retaining links by vote threshold. Our pipeline ranked third on evidence identification (Strict Micro F1 62.90), ninth on answer generation (Overall 31.90), and fifth on answer-evidence alignment (F1 79.81). A post-hoc linguistic analysis of 45 stylistic features reveals that model outputs remain 3.2 Flesch-Kincaid grade levels harder to read than clinician-authored references despite matching their word and sentence counts, suggesting readability warrants explicit optimization in clinical NLP systems. Code and prompts are available at https://github.com/mo-arvan/archehr-qa-2026-uic-aihealth4all.

cs.CL↗

arXiv2026

On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels

In multi-party dialogues between a dialogue system and multiple users, identifying to whom an utterance is addressed is a key challenge. Prior work has typically treated addressee detection as a multi-class classification task, selecting a single label representing an individual participant or the group. This formulation assumes that address is inherently discrete and has primarily been used for predicting turn-taking. In this paper, we revisit this assumption by analyzing address as a continuous phenomenon. Using a multi-party human dialogue corpus annotated by multiple annotators, we construct both binary address labels derived from majority-vote addressee labels and continuous address levels inferred from annotator judgments using a latent-variable model. We then examine how these representations relate to turn-taking as well as listener behaviors, including gaze and backchannels. Our results show that, in addition to turn-taking, both gaze and backchannels are associated with address. Furthermore, models using continuous address levels achieve better predictive fit than those using discrete labels, suggesting that address may exhibit graded structure. Finally, we discuss the future directions of addressee detection research based on the findings of this study.

cs.CL↗

arXiv2026

Not All Explanations Are Sought: Information-Seeking Psychology for Human-Centered XAI

This position paper argues that human-centered explainable AI (HCXAI) should incorporate insights from the psychology of information seeking. Drawing on Sharot and Sunstein's framework of information-seeking motives, we propose that people evaluate whether to engage with explanations based on three types of expected utility: instrumental (will it help me act better?), hedonic (will it make me feel better?), and cognitive (will it improve my understanding?). Each utility is estimated through a lens shaped by well-documented cognitive biases, including illusion of control, automation bias, unrealistic optimism, impact bias, overconfidence, and confirmation bias. These biases can lead to two failure modes: excessive information-seeking that fragments attention without improving decisions, and insufficient information-seeking that leaves critical risks and misunderstandings unexamined. This challenge is particularly acute for agentic AI systems, where explanations must support not just understanding a single output but anticipating cascading actions, assessing risks, and deciding when to intervene. By integrating information-seeking psychology into HCXAI, we advocate for a shift from making explanations available to making them sought: designing systems that account for when and why users actually want to know.

cs.AI↗

arXiv2026

The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models

As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according to the user's emotional state has become an important safety problem. We test whether emotional expression increases a model's endorsement (encouragement to proceed) when a user, holding the same objective information, is overconfident about a premature decision (e.g., quitting a stable job on weak evidence). As a key control, we include a no-emotion multi-turn (neutral) condition that holds factual content and the number of conversational turns constant, isolating the effect of emotion from that of conversation length. We exposed six commercial models (top-tier and mid-tier models from OpenAI, Anthropic, and Google) to three scenarios (career change, business expansion, emigration) across three conditions (cold/neutral/distress) with six repetitions each, yielding 324 conversations, and measured endorsement strength (0-100) via an eight-item rubric-based automated scoring. Emotional expression significantly increased endorsement (neutral 18.6 to distress 31.5, +12.9 points; mixed-effects $β= +12.9$, $p < .001$; Cohen's d = 0.51), and this was not explained by conversation length (cold-neutral difference non-significant, $p = .083$). Critically, the vulnerability varied by individual model rather than by price tier: five of six models showed a significant emotion effect, including the top-tier flagships Gemini 3.1 Pro and GPT-5.5, while only Claude Opus showed no significant change. Results were reproduced with an independent non-Google judge model ($ρ= .89$) and agreed in rank with two human coders ($ρ= .70$). Through a controlled design that separates emotion from conversational context, we show that emotional context increases LLM sycophancy even in top-tier flagship models.

cs.CL↗

arXiv2026

FocusBuddy: Encouraging Healthy Desk-Work Habits by Caring for a Virtual Pet on a Water Bottle

People who study or work at a desk sit for long uninterrupted periods and drink less water than they intend to. Software reminders address both problems but are easy to dismiss and easy to resent. We present FocusBuddy, a proof-of-concept fabric case that wraps a standard water bottle and houses a microcontroller, environmental sensors, and a small display showing a virtual pet. The pet's condition mirrors the user's self-care: drinking water feeds the pet, standing up to move plays with it, and refilling an empty bottle cleans it. Twenty undergraduate students used FocusBuddy for two weeks during their regular coursework and completed a written interview. Self-reported water intake rose from a median of 3 to 4 cups per day, movement episodes rose from 2 to 4 per day, and interviews surfaced two tensions: that wellness prompts must respect focused work, and that pet neglect can convert a wellness prompt into a source of guilt. We contribute the prototype, first-deployment evidence of healthy-direction shifts in self-reported habits, and design implications for emotionally framed wellness devices.

cs.HC↗

arXiv2026

MorphPatch: Enhancing VR Interaction on Shape Displays using Surface Approximation and Visuo-Haptic Illusions

On-surface interaction in Virtual Reality improves input performance through physical support and tactile feedback, but current shape displays are constrained by limited resolution. This can misalign physical and virtual surfaces, degrading usability and user experience. We present MorphPatch, a system that enables real-time alignment between a dynamic shape display and virtual surfaces. MorphPatch uses a Signed Distance Field-based surface approximation pipeline to find practical alignments for diverse geometries. For residual discrepancies, MorphPatch incorporates pen redirection with visuo-haptic illusion to perceptually compensate for misalignment. Three evaluations show improved geometric alignment, tolerable redirection thresholds, and better control, surface guidance, and modeling results over mid-air and tablet-like interaction.

cs.HC↗

arXiv2026

'A bit of chaos and madness': The AI Assessment Scale and the work of assessment reform

Generative artificial intelligence (GenAI) has intensified pressure on universities to redesign assessment while maintaining integrity, equity, and validity. Structured frameworks such as the Artificial Intelligence Assessment Scale (AIAS) offer one response, but evidence of how staff experience their implementation remains limited. This qualitative study examines AIAS implementation at a private international university in Vietnam and a public university in the United Kingdom. Data from five focus groups with 30 academic staff were analysed using hybrid thematic analysis, with Critical AI Literacy used as a sensitising concept. Six themes were developed: recognising and integrating AI, facilitating conditions, building capacity, pathways to adoption, ethics in practice, and reframing pedagogy. Staff valued the AIAS as a shared language for legitimising GenAI use, clarifying boundaries, and prompting reflection on assessment design. However, implementation was shaped by governance, tool access, staff confidence, workload, integrity concerns, disciplinary context, and alignment with learning outcomes. The findings show that the AIAS could prompt authentic assessment design and student engagement, but may become a compliance layer when disconnected from learning outcomes, disciplinary context, and staff capacity. This study contributes empirical evidence on the institutional conditions through which GenAI assessment frameworks move from policy adoption to pedagogical enactment.

cs.HC↗

arXiv2026

From Preventive to Reactive: How AI Coding Assistants Transform Developers' Security Awareness

AI coding assistants are now central to professional software development, yet their impact on how developers think about and practice security remains poorly understood. While prior work has documented vulnerability rates in AI-generated code, a more fundamental question persists: how do these tools transform security awareness in authentic, ongoing development practice? We conducted semi-structured interviews with 15 professional software engineers and observed them completing security-relevant coding tasks with AI assistance, spanning 3 experience cohorts defined by their relationship to AI tools during professional formation. We find that AI coding assistants reorganize rather than eliminate security thinking, shifting it from the act of writing code to the act of reviewing it. This transition from preventive to reactive security is structurally encouraged by interaction models that frame code generation as a functional task, leaving security as an afterthought. Notably, none of our coding session participants specified security requirements in their initial prompts, even when they possessed the relevant knowledge, revealing a decoupling of security awareness from security behavior. We further document informal coping strategies developers had independently invented to manage AI security risk, none of which are supported by current tools or organizations, and find that the experience cohort did not reliably predict security performance. This paper contributes a practice-grounded account of how AI-assisted development reshapes the human side of secure coding, offering empirical foundations for the design of more security-aware tools, training programs, and organizational policies.

cs.HC↗

arXiv2026

Seeing Without Understanding: Large Language Model Evaluation of Mobile User Interface Quality, Failure Taxonomy, and Architectural Explanation

Evaluating mobile user interface quality at scale remains a persistent challenge in software engineering and human-computer interaction. Rule-based heuristic methods offer structural reliability but demand significant engineering effort, while human annotation does not scale to the volume of applications produced annually. Large language models present a promising alternative, yet their reliability for structured UI judgment has not been systematically examined, and the patterns behind their failures remain insufficiently characterized. This paper addresses both gaps. We begin with the complete RICO dataset of 66,261 real-world mobile application screens, from which we derive a refined evaluation corpus of 15,000 screens through a rigorous, literature-guided selection process. Each screen is assessed across seven criteria: structural JSON validity, minimum visible element count, clickable component presence, non-zero layout bounds, image integrity, and perceptual duplicate removal. Against this corpus, we apply a heuristic baseline built from severity-weighted usability signals, normalized layout metrics, and pixel-ratio complexity measures calibrated to real user sentiment. Multiple language models independently rate each screen across usability, layout quality, and visual complexity from structured JSON descriptions and raw screenshots. Dimension-level comparison against the heuristic uses agreement rates, Cohen's Kappa, and confidence calibration. Recurring divergence patterns are organized into a failure taxonomy and interpreted through transformer architectural signatures: MLE plausibility bias, attention misgrounding, and autoregressive over-commitment.

cs.HC↗

arXiv2026

Auditing Bias and Safety in Voice AI Customer Care

Voice AI systems increasingly mediate customer care interactions where caller presentation cues such as accent, affect, fluency, and urgency are available alongside the service request. Existing fairness and safety evaluations cover speech recognition disparities, spoken dialogue bias, and voice agent capability, but rarely treat customer care voice agents as stateful, multi turn, tool mediated systems where harm can appear as additional burden before any final denial occurs. We formalize a validation gated audit framework for such systems. The framework (i) separates native speech to speech, cascaded ASR to language model to TTS, and hybrid tool mediated architectures; (ii) uses matched service facts across controlled caller presentation conditions; (iii) validates fact invariance, presentation cues, artifacts, and acoustic measurements before inference; and (iv) records both material outcomes and path to service burden. We define the research problem, methodology, seven validation gates, a six family metric set, and claim boundaries for an active industry evaluation program. We illustrate the framework with a fully synthetic worked example of a refund dispute audit instance. Production system results are excluded from this release; public reporting is gated by the validation protocol.

eess.AS↗