arXiv subjects

Yuntao Wang

Publications and source records attributed to Yuntao Wang.

At least 19 recordsLinked to original sources

arXiv2026

StoryEcho: A Narrative Mirroring Loop Generative Storytelling System for Picky-Eating Intervention

Picky eating can limit children's dietary variety and create tension in family feeding routines. Existing food-related technologies often focus on mealtime intervention or standalone educational artifacts, offering limited support for connecting low-pressure narrative engagement with children's real-world food exploration over time. We present StoryEcho, a generative storytelling system centered on a narrative mirroring loop, in which personalized stories model sensory exploration through a persistent counterpart and children's subsequent food encounters are reflected back into narrative feedback and future story development. Informed by a formative study, we designed StoryEcho and evaluated it in a 14-day between-subjects field study with 26 families. Compared with food-personalized generative stories without the narrative mirroring loop, StoryEcho was associated with higher try level, approach, and intake, and lower resistance and caregiver pressure. These findings suggest that narrative mirroring can support children's low-pressure food exploration in family routines, while highlighting design tensions for future generative storytelling interventions.

cs.HC↗

arXiv2026

Fail-closed conformal multiresolution error control for conservative three-dimensional dose remapping in synthetic phantoms

Conservative dose remapping can be formulated by transporting mass and deposited energy across nonmatching grids, but fixed high-sampling calculations use the same work for easy and difficult cases. We developed conformal multiresolution error control (CoMERC), a fail-closed multilevel quasi-Monte Carlo (QMC) controller for reference-relative target-cell allocation error in a fixed piecewise-constant source model with known deformation. Two randomized nested replicates were evaluated at a probe level of 4 and candidate levels of 8 and 16. Four endpoints were controlled jointly: reference-mass-weighted global, high-gradient, and density-gradient-threshold root-mean-square error, plus eligible-cell maximum absolute error. A split-conformal multiplier was calibrated from 240 synthetic cases, frozen, and evaluated on 400 independent cases from the same generator and 120 cases from a prespecified shifted generator. In the primary set, joint coverage was 394/400 (98.50%; one-sided 95% lower limit, 97.06%), 388/400 cases (97.00%; lower limit, 95.18%) received an output, and 0/388 released outputs exceeded any tolerance (one-sided 95% upper limit, 0.769%). Final actions were level 8 for 190 cases, level 16 for 198, and ABSTAIN for 12. The frozen policy implied mean relative production-sample work of 0.5844 compared with always running both randomized replicates through level 16; the prespecified 95th-percentile bootstrap upper limit was 0.6194. All seven primary gates passed. In the shifted-generator set, 113/120 cases were released and one released output exceeded a tolerance. CoMERC provided marginal finite-sample error control and lower modeled production-sample work in the locked synthetic population, but not patient-level, registration-level, conditional-on-release, or clinical safety validation.

physics.med-ph↗

arXiv2026

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. Each model serves as a complete conversational frontend, integrating continuous perception, conversational control, and native speech generation through a shared causal timeline for user inputs, model outputs, and delegation events. A dual-loop runtime coordinates live interaction with background reasoning and tool execution. Foreground interaction continues while Realtime-Venus-Harness executes tasks asynchronously and returns results for integration into the ongoing dialogue. Both models follow a common post-training recipe combining offline understanding, proactive full-duplex trajectories, and delegation workflows. Among the evaluated online models, Realtime-Venus-Omni achieves the highest scores on six of eight video benchmarks, including StreamingBench (70.2%), OVO-Bench (64.7%), and Daily-Omni (81.3%). Across eight audio understanding and spoken question answering benchmarks, Realtime-Venus-Audio leads the compared models on MMAU (78.0%), MMAU-Pro (63.2%), Llama Questions (83.8%), and Speech CMMLU (67.8%), while matching the best VoiceBench AlpacaEval score of 4.81. On Full-Duplex-Bench v1.5, Realtime-Venus-Audio responds to 75% of user interruptions and achieves continuation rates of 97%, 88%, and 86% under backchannels, other-directed speech, and background speech, respectively, exceeding Gemini 3.1 Live and GPT-4o on all three continuation metrics.

cs.CV↗

arXiv2026

Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments

Positive everyday moments often escape deliberate recording, while continuous self-tracking can generate extensive records that are difficult to revisit. We explore laughter as a naturally occurring, sparse index for constructing contextualized personal records to support later reconstruction and reflection. A formative study with 12 participants characterized laughter as an affective but semantically incomplete index and informed \textit{LaughAnchor}, a mobile and wearable self-tracking system. During participant-initiated recording, the system assembles detected laughter and aligned context into candidate moments for later reconstruction and reflection, with layered context disclosure, user-controlled curation, and near-term and long-term resurfacing. In a three-week field deployment with 12 participants, passive indexing preserved moments they considered unlikely to record deliberately but valued retrospectively. During resurfacing, participants attributed affective re-experiencing to laughter and used additional context both to reconstruct episodes and to explore already-recalled experiences. Across moments and reviews, resurfacing supported rediscovery and broader awareness of relationships, routines, and emotional states. These findings inform self-tracking designs that use sparse affective indices to organize contextual records for reconstruction and reflection, while keeping interpretation and retention under user control.

cs.HC↗

arXiv2026

Earinter: A Closed-Loop System for Eating Pace Regulation with Just-in-Time Intervention Using Commodity Earbuds

Rapid eating is common yet difficult to regulate in situ, partly because people seldom notice pace changes and sustained self-monitoring is effortful. We present Earinter, a commodity-earbud-based closed-loop system that integrates in-the-wild sensing, real-time reasoning, and theory-grounded just-in-time (JIT) intervention to regulate eating pace during daily meals. Earinter repurposes the earbud's bone-conduction voice sensor to capture chewing-related vibrations and estimate eating pace as chews per swallow (CPS) for on-device inference. With data collected equally across \modify{sessions in quiet and noisy environments}, Earinter achieves reliable chewing detection (F1 = 0.97) and accurate eating pace estimation (MAE: 0.18 $\pm$ 0.13 chews/min, 3.65 $\pm$ 3.86 chews/swallow), enabling robust tracking for closed-loop use. Guided by Dual Systems Theory and refined through two Wizard-of-Oz pilots, Earinter adopts a user-friendly design for JIT intervention content and delivery policy in daily meals. In a 13-day within-subject field study (N=14), the closed-loop system significantly increased CPS and slowed meal-level eating pace, with statistical signs of carryover on retention-probe days and generally favorable comfort and usability. These effects should be interpreted as changes in eating-pace regulation rather than evidence of weight loss. Our findings highlight how single-modality commodity earables can support practical, theory-driven closed-loop JIT interventions for regulating eating pace in the wild.

cs.HC↗

arXiv2026

Towards Wearable Opportunistic Crowdsensing for Open-Vocabulary Activity Data Collection Through User-Scheduled Trigger-Action Routines

Collecting richly labeled wearable activity data in everyday settings remains difficult because retrospective annotation is costly and often imprecise. Prior data collection apps rely on a labor-intensive self-reporting strategy and primarily treat participants as crowd labelers. We present Pebbl, a feasibility-stage system that incentivizes in-situ labeling through opportunistic crowdsensing. Pebbl lets users author trigger-action recipes on a smartphone and receive just-in-time reminders for beneficial actions when a trigger is detected. In the prototype, triggers are a limited set with four common audio cues, while actions are described in open-vocabulary natural language. Each confirmed execution yields a short sensor window with explicit start/end boundaries and a user-authored action label. We evaluate Pebbl through an expert workshop with wearable Human Activity Recognition (HAR) researchers (N = 6), a within-subject in-lab study (N = 21), and a pilot deployment (N = 8). Experts viewed the approach as lower burden and more ecologically valid than common labeling workflows. In the lab, Pebbl produced reliable execution logs under controlled conditions (recall = 97.30%, precision = 97.15%) and was preferred over comparison workflows on perceived burden and confidence. The pilot deployment shows that the interaction and sensing pipeline can function in free-living use, while surfacing practical constraints such as false triggers and context dependence. Overall, Pebbl represents a step toward a low-burden, distributable collection approach of user-contributed wearable activity data.

cs.HC↗

arXiv2026

VergeIO: Depth-Aware Eye Interaction on Glasses

There is growing industry interest in unobtrusive designs for electrooculography (EOG) sensing of eye gestures on glasses (e.g. JINS MEME and Apple eyewear). We present VergeIO, an EOG-based glasses system that enables depth-aware eye interaction by sensing vergence with a glasses-compatible electrode layout and smart glass prototype. It can distinguish between four depth-based eye gestures with 97% accuracy on unseen users without any calibration in a user study across 20 users and 1,520 gesture instances. To reduce false detections, we incorporate a motion artifact detection pipeline and a preamble-based activation scheme. The system uses dry sensors without any adhesives or gel and operates in real time with 3 mW power consumption by the analog sensing front-end.

cs.HC↗

arXiv2026

MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein

Multimodal Large Language Models (MLLMs) inherit rich relational priors from their language backbones, yet often fail when asked to apply these relationships in visual contexts. We trace this failure to a structural blind spot: projection-based alignment trains each visual token to carry the right semantics, but never asks whether the relationships between concepts survive the crossing from language to vision. To address this, we propose MIRROR (Mapping Inter-concept Relations from language to visual Representation via Optimal-transport-based Regularization), a geometric regularization framework that transfers relational priors from language to vision by exploiting the rich relational structure encoded in language representations. Specifically, we derive a surrogate loss from the proposed Semi-Inverse Gromov-Wasserstein (SI-GW) problem, an inverse geometric problem that aligns visual representations with language-derived relational priors. We show that this formulation admits a unique closed-form solution that prescribes the ideal visual relational structure implied by language geometry and cross-modal coupling. The structure of the formulation also enables efficient computation, making it applicable to long token sequences. Applying SI-GW inside decoder-only Transformers requires careful design. We introduce targeted strategies at the layer, head, and token levels to ensure stable extraction without additional parameters or inference cost. MIRROR improves relational consistency while preserving performance on general vision-language tasks.

cs.CV↗

arXiv2026

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential. This paper introduces explicit personality conditioning and establishes a systematic evaluation framework encompassing single-personality induction, multi-personality induction, and personality switching. Experiments show that personality induction improves image captioning performance but can impair performance on tasks requiring precise reasoning, such as visual question answering (VQA). Balancing and residual effects are observed during multi-trait composition and dynamic switching, indicating that model behavior is co-modulated by both previous and current personality constraints. Existing prompt-based personality induction methods show limited transferability to multimodal settings. Our work reveals the dynamic and complex nature of personality modeling in MLLMs and underscores the need for robust, tailored methods for personality induction and evaluation. The code will be released when the paper is accepted.

cs.CL↗

arXiv2026

Secure UAV Swarms in Low-Altitude Wireless Networks: Challenges and Solutions

Unmanned aerial vehicle (UAV) swarms are increasingly deployed in vast low-altitude applications, owing to their capabilities in distributed sensing, flexible communication, and autonomous coordination. Nevertheless, the open and highly dynamic operating environment of UAV swarms introduces serious security risks, including GPS spoofing, insider threats, and multi-hop intrusion. These threats are aggravated by limited on-board resources, frequently changing network topology, and the presence of intelligent adversaries. To tackle these issues, this paper proposes a cloud-edge-end collaborative defense framework for UAV swarms. Based on this framework, three complementary mechanisms are developed. First, a cooperative perception scheme is designed to resist GPS spoofing via interactive attack-defense game modeling. Second, a behavior-driven authentication method with trust evaluation is developed to mitigate insider threats. Third, a multi-agent attack forensics framework is devised to intelligently trace the propagation paths of multi-hop attacks in UAV networks. Experimental results validate the effectiveness of the proposed approaches. Finally, several open research directions are outlined.

cs.CR↗

arXiv2026

Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures

The rapid evolution of large language model (LLM)-driven autonomous agents has given rise to OpenClaw, a new class of open-source agent frameworks that operate as continuously running, skill-augmented systems with persistent memory, multi-channel interaction, and high degrees of autonomy. Such capabilities enable OpenClaw agents to autonomously execute complex, multi-step tasks and interact seamlessly with external applications, but simultaneously introduce a substantially enlarged attack surface. In particular, the combination of high-privilege operations and persistent memory exposes OpenClaw agents to various emerging threats, including skill poisoning, cognitive manipulation, multi-agent cascading failures, and supply-chain vulnerabilities. In this survey, we present a comprehensive study of the security landscape of OpenClaw agents. We first examine the general architecture and key characteristics that distinguish OpenClaw agents from traditional AI agent systems. We categorize existing security and privacy threats into a layered framework and analyze how vulnerabilities arise during agent reasoning, action execution, and external interaction. Representative defense mechanisms are also reviewed to draw the current defense landscape. Finally, several unresolved issues related to the reliability and trustworthiness of OpenClaw ecosystems are discussed.

cs.AI↗

arXiv2026

Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions

Large language models (LLMs)-empowered autonomous agents are transforming both digital and physical environments by enabling adaptive, multi-agent collaboration. While these agents offer significant opportunities across domains such as finance, healthcare, and smart manufacturing, their unpredictable behaviors and heterogeneous capabilities pose substantial governance and accountability challenges. In this paper, we propose a blockchain-enabled layered architecture for regulatory agent collaboration, comprising an agent layer, a blockchain data layer, and a regulatory application layer. Within this framework, we design three key modules: (i) an agent behavior tracing and arbitration module for automated accountability, (ii) a dynamic reputation evaluation module for trust assessment in collaborative scenarios, and (iii) a malicious behavior forecasting module for early detection of adversarial activities. Our approach establishes a systematic foundation for trustworthy, resilient, and scalable regulatory mechanisms in large-scale agent ecosystems. Finally, we discuss the future research directions for blockchain-enabled regulatory frameworks in multi-agent systems.

cs.AI↗

arXiv2026

EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning

Despite extensive efforts on egocentric video datasets and benchmarks, understanding users' internal states, which is crucial for enabling seamless AI assistant experiences, remains largely overlooked. In this work, we introduce EgoIntrospect, the first egocentric dataset captured in user-driven scenarios with self-annotations that explicitly reveal users' interactive intentions with AI assistants. EgoIntrospect was collected using a cross-device setup, providing synchronized video, audio, gaze, motion, and physiological signals. It consists of 180 hours of recordings from 60 subjects, with an average recording duration of 3 hours per subject. Leveraging EgoIntrospect, we formalize a suite of tasks centered on user internal states, including affective experience, interactive intent, and cognitive memory. We further process the annotations to construct benchmarks that evaluate the ability of modern multimodal large language models to reason about users' internal states from egocentric observations. Experiments on our benchmark suggest that existing multimodal large language models struggle to effectively leverage multimodal signals to infer users' subjective internal states. The dataset and annotations will be made publicly available to advance research in egocentric vision and wearable AI assistants. Project page: https://ego-introspect.github.io/

cs.CV↗

arXiv2026

AuthGlass: Benchmarking Voice Liveness Detection and Authentication on Smart Glasses via Comprehensive Acoustic Features

With the rapid advancement of smart glasses, voice interaction has been widely adopted due to its naturalness and convenience. However, its practical deployment is often undermined by vulnerability to spoofing attacks, while no public dataset currently exists for voice liveness detection and authentication in smart-glasses scenarios. To address this challenge, we first collect a multi-acoustic-modal dataset comprising 16-channel audio data from 42 subjects, along with corresponding attack samples covering two attack categories. Based on insights derived from this collected data, we propose AuthG-Live, a sound-field-based voice liveness detection method, and AuthG-Net, a multi-acoustic-modal authentication model. We further benchmark seven voice liveness detection methods and four authentication methods across diverse acoustic modalities. The results demonstrate that our proposed approach achieves state-of-the-art performance on four benchmark tasks, and extensive ablation studies validate the generalizability of our methods \red{under real-world constraints}. Finally, we release this dataset, termed AuthGlass, to facilitate future research on voice liveness detection and authentication for smart glasses.

cs.HC↗

arXiv2026

Vol-Mark: A Watermark for 3D Medical Volume Data Via Cubic Difference Expansion and Contrastive Learning

Today, advances in medical technology extensively utilize 3D volume data for accurate and efficient diagnostics. However, sharing these data across networks in telemedicine poses significant security risks of data tampering and unauthorized copying. To address these challenges, this paper proposes a novel reversible-zero watermarking approach, termed Vol-Mark, for medical volume data to protect their ownership and authenticity in telemedicine. The proposed Vol-Mark method offers two key benefits: 1) it designs a volume data feature extractor that leverages contrastive learning to efficiently extract discriminative and stable volumetric features, ensuring robustness against 3D attacks; 2) it introduces the cubic difference expansion (c-DE) technique, which leverages the 3D integer wavelet transform to embed watermark bits into neighboring voxels within cubes at low-frequency coefficients. The voxel differences within each cube are expanded to create embedding space, and a majority voting mechanism is employed during extraction to enhance reliability. The embedding process incurs low distortion and supports lossless removal, thereby preserving the integrity and diagnostic accuracy of medical volume data. Through these two benefits, Vol-Mark enables both integrity verification and ownership verification. Integrity verification is first performed, and ownership verification through hypothesis testing is further conducted to enhance reliability, particularly under data tampering or watermark removal attacks. Comprehensive experimental results show the effectiveness of the proposed method and its superior robustness against conventional, geometric, and hybrid attacks on medical volume data. In particular, through multiple tasks evaluations, Vol-Mark consistently achieves an ACC above 0.90 in most attack scenarios, outperforming existing methods by a clear margin.

cs.CR↗

arXiv2026

LubDubDecoder: Bringing Micro-Mechanical Cardiac Monitoring to Hearables

We present LubDubDecoder, a system that enables fine-grained monitoring of micro-cardiac vibrations associated with the opening and closing of heart valves across a range of hearables. Our system transforms the built-in speaker, the only transducer common to all hearables, into an acoustic sensor that captures the coarse "lub-dub" heart sounds, leverages their shared temporal and spectral structure to reconstruct the subtle seismocardiography (SCG) and gyrocardiography (GCG) waveforms, and extract the timing of key micro-cardiac events. In an IRB-approved feasibility study with 25 users, our system achieves correlations of 0.88-0.95 compared to chest-mounted reference measurements in within-user and cross-user evaluations, and generalizes to unseen hearables using a zero-effort adaptation scheme with a correlation of 0.91. Our system is robust across remounting sessions and music playback.

cs.HC↗

arXiv2026

SpeakSoftly: Scaffolding Nonviolent Communication in Intimate Relationships through LLM-Powered Just-In-Time Interventions

Conflicts are common in text-based communication, particularly in intimate relationships, where misunderstandings can easily escalate into verbal aggression. To address this, we present SpeakSoftly, a system that applies Nonviolent Communication (NVC) principles to scaffold couples' conflict communication through LLM-powered just-in-time interventions. Informed by formative interviews with couples and NVC principles, we designed two core features: NVC-Prompt, which detects verbal aggression and suggests revisions to prevent escalation, and NVC-Guide, which analyzes dialogues to uncover users' feelings and needs, fostering self-awareness and perspective-taking. These features were implemented across three progressive intervention modes, each varying in intervention depth and tone: Basic Reminder, Neutral Guide, and Empathetic Guide. We conducted a mixed-methods user study with 18 couples across simulated and real-life conflict settings to evaluate the effectiveness of each mode. Results showed that Empathetic Guide significantly facilitated both behavioral and cognitive changes, while Neutral Guide was effective only for behavioral changes in simulated conflicts. In real-life conflicts, Neutral Guide showed distinct advantages due to lower cognitive load demands. We discuss the mechanisms behind these findings and propose design implications for in-situ interventions in high-stakes communication contexts.

cs.HC↗

arXiv2026

Exploring and Analyzing the Effect of Avatar's Visual Style on Anxiety of English as Second Language (ESL) Speakers

Virtual avatars offer new opportunities to reshape communication experiences beyond traditional live video. However, it remains unclear how avatar representations influence communication anxiety for English as a Second Language (ESL) speakers, and why such effects emerge. To take a first step to address this, we conducted a controlled laboratory study in which Mandarin-speaking ESL participants engaged in one-on-one conversations under three representation conditions: live video, stylized avatars, and realistic avatars. We assessed anxiety using both self-reported measures and physiological signals (EDA, ECG, PPG). Our results show that avatar style plays a critical role in shaping communication anxiety. While live video remained a strong baseline with low subjective anxiety, stylized avatars achieved comparable-and in some cases lower-physiological anxiety levels, whereas realistic avatars elicited higher anxiety. Beyond these effects, our findings reveal three underlying mechanisms that explain how avatar representations shape ESL communication anxiety: (1) facial expressiveness; (2) perceived feedback and fear of negative evaluation; and (3) contextual appropriateness. This work provides actionable design implications for developing avatar-mediated communication systems that support emotionally sustainable cross-linguistic interaction.

cs.HC↗