arXiv subjects

Xin Yi

Publications and source records attributed to Xin Yi.

At least 19 recordsLinked to original sources

arXiv2026

CoVer: Conflict-Aware Claim Verification

Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative news sources. To capture this challenge and support conflict verification tasks, we present ContraNote, a large-scale real-world dataset curated from X's Community Notes system. It includes 33,686 posts for evaluating evidence-level conflict resolution, and 54,474 instances for evaluating aggregation-level prioritization. Additionally, we propose CoVer, a factual adjudication framework with three-stage pipelines: evidence schema normalization, factual consensus and support verification. This prioritizes evidence over noise to prevent it from compromising the final verdict. Technical evaluations show that CoVer achieves strong performance compared with state-of-the-art baselines across ContraNote (86.0% Acc., 68.0% mac. F1, 64.5 bal. Acc. on Conflict; and 88.5% Acc., 88.5 mac. F1 and 89.2 bal. Acc. on Prioritization), CONFACT-HumC (88.4% Acc.) and CONFACT-ModC (89.4% Acc.).

cs.AI↗

arXiv2026

Position: Robot Privacy as Embodied Boundary Work. Connecting Capabilities, Contexts, and Design Responses in Everyday Robotics

Robots are increasingly entering everyday environments where privacy is shaped not only by data practices, but also by spatial, bodily, social, and relational boundaries. Their embodied capabilities allow them to reshape these boundaries through situated action, challenging privacy framings centered on data flows, interface settings, or one-time consent. Prior work has examined robot privacy through sensing, data collection, telepresence, transparency, consent, bystander awareness, and multi-stakeholder governance. Building on this work, we propose embodied boundary privacy as a capability-by-context framing for examining how physically present robots may reshape privacy boundaries in situated interaction. Specifically, this framing organizes privacy risks across seven robot capabilities and five deployment contexts, asking how embodied capabilities enable boundary crossings and how situated contexts shape who is affected, how these crossings are interpreted, and when they become contested. We use this perspective to outline design and research implications for embodied privacy mechanisms, including boundary checkpoints, viewpoint-aware sensing control, remote-presence disclosure, object- and body-level access rules, constraints on socially persuasive privacy influence, and local interruption rights. We encourage HRI research, design, and governance to treat robot movement, orientation, proximity, object access, remote presence, and social expression as privacy-relevant actions whose meaning depends on context.

cs.RO↗

arXiv2026

Aicir: A Full-Stack Quantum Circuit Simulator with AscendNPU Support

Quantum computing is a promising way to study problems that are difficult for classical methods, but current quantum hardware still faces limits in scale, noise, and fidelity. Running quantum algorithms on physical machines can also be costly. Quantum circuit simulators therefore remain important because they let researchers design and test algorithms on classical computers before using quantum hardware. Most high-performance simulators provide GPU backends, while few offer native support for NPUs. This gap limits the computing platforms available for quantum-algorithm research. We developed Aicir to provide a full-stack quantum circuit simulator with a native Huawei Ascend NPU backend. Aicir connects circuit construction, several state representations, measurement, differentiation, variational algorithms, quantum machine learning, and quantum architecture search through one programming model. It also supports noise simulation, tensor-network and matrix-product-state engines, and distributed state simulation. On the NPU, paired real tensors, fixed-rank gate views, and hardware-specific formulas keep the tested simulation paths on the device. The same representation lets Aicir partition a state across $2^{p}$ NPUs while retaining reverse-mode differentiation. We validated native execution with CPU fallback disabled and checked distributed communication and gradients on 2, 4, and 8 NPUs. For the tested fused layered circuits, Aicir's CPU runtime is within $0.97$--$1.28\times$ that of Qiskit Aer and $0.76$--$1.10\times$ that of Cirq. These results place its CPU execution in the same range as established simulators for this workload, while the NPU tests establish correct native execution rather than CPU-to-NPU speedup.

quant-ph↗

arXiv2026

Understanding Security and Privacy Perceptions of Content Creators Regarding AI Labels of AI-Generated Content

AI labels, typically implemented via underlying tracing mechanisms such as watermarks and metadata, are crucial for protecting Artificial Intelligence-Generated Content (AIGC) against security threats like disinformation and evasion. However, the perceived devaluation of AI-assisted work discourages creators from disclosing AI use, incentivizing efforts to bypass labeling and compromising downstream traceability. Yet, how AIGC creators perceive the security and privacy (S\&P) implications of these labels, and how their behaviors impact technical resilience remain underexplored. To this end, we conducted semi-structured interviews with 21 AIGC creators and measured images across 6 image generation platforms against 16 self-reported manipulation settings. Our findings reveal that creators conflate binary AI labels with granular traceability, and express strong fears of de-anonymization via platform identifiers. Driven by fears of algorithmic traffic suppression and reputational risks, they defensively removed digital traces. Through empirical tests, we show that targeted modifications like coarse quantization significantly degrade detection. AI detection capabilities are also inconsistent across platforms, and suffer from false positives even for human-authored images. Based on these insights, we advocate for workflow-resilient implicit AI labels that align technical guarantees with creators' incentives.

cs.HC↗

arXiv2026

Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks

Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs). However, current evaluation benchmarks remain disproportionately fixated on Text-to-SQL tasks, neglecting the holistic Database Lifecycle-from initial schema design to post-deployment maintenance. This narrow focus fails to capture the diverse capabilities required for real-world database management. To bridge this gap, we introduce DBLifeBench, the first benchmark to evaluate LLMs across five critical lifecycle phases: Design, Implementation, Operation, Debugging, and Maintenance. Furthermore, addressing the cognitive mismatch between ambiguous natural language and complex SQL logic, we propose Progressive-Text2SQL, a novel task utilizing structured reasoning graphs to mimic human iterative problem-solving. Our extensive evaluation reveals a critical insight: while general-purpose models demonstrate balanced performance, specialized Text-to-SQL models suffer from ``catastrophic forgetting'' in non-coding phases like design and maintenance. DBLifeBench serves as a foundational step toward evaluating and building true full-stack database intelligence.

cs.DB↗

arXiv2026

Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models

Large language models (LLMs) are costly intellectual assets that remain exposed to unauthorized redistribution and commercial misuse. Injected fingerprints, i.e., trigger--target pairs embedded in model behavior, offer a practical, black-box-verifiable ownership signal, but existing methods decouple the two stages of the fingerprint life cycle: how a fingerprint is constructed and how it is injected. Existing fingerprinting frameworks suffer from two limitations. Natural-language fingerprints are prone to accidental activation, and garbled fingerprints are easily filtered by perplexity-based detection. Furthermore, decoupling construction from injection leaves the latter unaware of the trigger's linguistic structure, missing the opportunity for targeted optimization. We argue that fingerprint construction should drive injection, and present a unified fingerprinting framework that jointly optimizes both stages. First, LCF constructs code-mixing fingerprints by combining low-resource languages under a semantic-density substitution rule and grammar-biased mixing, yielding triggers whose perplexity sits far below garbled baselines while avoiding the accidental-activation failures of natural-language triggers. Second, LCFEdit injects each fingerprint with a null-space projection derived from high-resource multilingual representations that preserves knowledge, augmented by a cross-lingual alignment step that steers the weight update toward the fingerprint language's representation subspace. This construction-aware injection ensures that the update is linguistically informed and therefore more stable. Extensive evaluations on imperceptibility, detectability, and harmlessness demonstrate persistent ownership verification with negligible impact on utility.

cs.CL↗

arXiv2026

Is It Real? Exploiting Virtual-Physical Discrimination Vulnerability in Mixed Reality

Consumer mixed reality (MR) headsets seamlessly blend virtual content into physical environments with sufficient fidelity that users may be unable to distinguish virtual objects from physical ones. We identify this virtual-physical discrimination vulnerability as an exploitable security primitive. Through speculative design workshops with 12 experts from cybersecurity and MR/HCI, we develop a taxonomy of virtual-physical confusion attacks and implement four proof-of-concept attacks on Apple Vision Pro, evaluating them with 26 participants in realistic MR tasks. All four attacks altered user behavior, with success rates ranging from 85% to 100%, producing misdirected interactions, misjudged object identities, biased purchasing decisions, and altered navigation paths. Notably, the most successful attacks were also the hardest to detect according to participants' subjective ratings. Even participants who recognized virtual content still complied behaviorally, and no participant attributed anomalous events to adversarial causes. We propose platform-level provenance, interaction gating, and user education as countermeasures.

cs.HC↗

arXiv2026

CANote: Empowering Fact-checking Note Writing Through Scaffolded and Provenance-based Human-AI Collaboration

Crowdsourced fact-checking mechanisms, such as X's Community Notes, play a critical role in mitigating the spread of misinformation. However, drafting high-quality, evidence-based debunking notes imposes a substantial burden on contributors. We present CANote, an AI-assisted debunking note writing system featuring evidence correlation and structured co-drafting. CANote scaffolds the workflow by extracting subclaims from social media posts, providing provenance through explicit links between subclaims and retrieved evidence, and generating neutral, structural drafts to support human reasoning. We evaluated CANote against manual writing (N=52 fact-checkers, N=52 lay users) on simulated X platform, where we found CANote significantly improves note quality. Notably, CANote enables lay users to write notes that have comparable quality to those written by experts. While the task completion time and perceived cognitive load remain comparable to manual drafting, CANote significantly increases user satisfaction. However, this assistance introduces a trade-off, resulting in a reduced sense of user ownership and control over the debunking note.

cs.HC↗

arXiv2026

Towards Multi-Agent-Simulation-Based Community Note Evaluation

Community-based fact-checking that relies on cross-consensus is expanding rapidly on social media platforms. However, the delay and low-ratio of cross-consensus community fact-checks rated by human contributors remains a significant challenge. To address this, we first created ComRate, a large-scale dataset comprising 2.5 million community notes and over 209 million ratings sourced from $\mathbb{X}$. We then propose MultiCom, a persona-guided multi-agent rating framework for community note evaluation. MultiCom simulates diverse rater population by clustering contributors in a matrix-factorized rater space and prompting persona agents to generate structured assessments based on the official community notes rating schema. These agents output structured and explainable judgments, such as confidence, agreement signals and reasons. An out-of-fold calibrated aggregation algorithm combines features such as raw votes and diagnostic reason signals for reliable prediction. Extensive evaluations demonstrate that MultiCom outperforms alternative methods, achieving an average accuracy of 84.7% (balanced accuracy 68.3%, macro-F1 60.1%) on the evaluation set.

cs.SI↗

arXiv2026

Focused on the User, Overlooking the Risks: Security and Privacy Understandings, Practices and Challenges of Independent Chinese AI Agent Developers

The proliferation of AI agents empowers independent developers, defined as individual or small groups who self-initiate projects rather than fulfill client-based contracts, to create sophisticated autonomous systems, but also introduces novel security and privacy (S&P) challenges beyond traditional corporate structures. We conducted an interview study (N=28) with Chinese developers, whose extensive use of global LLM services offer valuable insights into this population. We investigate their understandings, practices and challenges of S&P challenges in their developed AI agent products. We revealed that independent developers frequently think and act from their users' perspective. They focused on user-facing safety risks such as harmful content while exhibiting low awareness of security vulnerabilities. Consequently, developers rely almost exclusively on ad-hoc, manually crafted safeguards and informal communication, with an absence of formal tools or processes for S&P practices. We found these actions are driven by various inhibitors, primarily a lack of formal training on S&P related skills, accessible security tools and actionable guidance from platforms. Our work contributed the first exploration of independent AI agent developers' S&P understanding, outlining opportunities for tailored security tooling.

cs.HC↗

arXiv2026

Generative AI-Enabled Refund Fraud in Chinese E-Commerce: Investigation on Merchants and Platform Workers

E-commerce dispute resolution typically relies on the security assumption that digital evidence truthfully reflects physical reality. Generative AI (GenAI) invalidates this threat model, enabling attackers to fabricate hyper-realistic evidence of product defects at negligible cost. Through semi-structured interviews with merchants (N=17) and platform workers (N=13) in the Chinese e-commerce market, we characterize this shift toward GenAI-enabled scalable fabrication. We outline a taxonomy of four GenAI-enabled threat vectors across the transaction, dispute, logistics and communication phases, highlighting how attackers exploit GenAI to synthesize physically plausible product defects at scale. To mitigate these threats, platforms and merchants are adapting verification strategies, relying on AI tools for automated screening and adversarial interrogation (e.g., requesting multi-angle videos) to increase attack complexity. However, we find several challenges that hinder the adoption of these defenses, including implementation hurdles like structural platform constraints and fundamental limitations regarding the technical sophistication of GenAI. We conclude by outlining design implications for privacy-preserving cross-platform fraud databases, and traceability mechanisms such as embedding verifiable material anchors into the product.

cs.CR↗

arXiv2026

Investigating Novice Researchers' Perceptions of Research Privacy Within LLM-Assisted Workflows

Large Language Model (LLMs)-assisted scholarly workflows introduce critical privacy and intellectual property risks. As a uniquely vulnerable cohort driven by publication pressure and a lack of institutional support, novice researchers rely heavily on public LLMs, compelling them to navigate high-stakes privacy-publication trade-offs. To investigate these concerns, we conducted semi-structured interviews with 44 researchers across diverse disciplines. Our findings reveal that the fear of idea leakage paradoxically accelerates, rather than deters, reliance on LLMs, as researchers utilize them to expedite publication. They also held misconceptions that their ideas lacked the unique value to attract targeted attacks, and that their inputs would be safely diluted within massive datasets, preventing reconstruction. From interviews, we identified five types of mitigations including input fragmentation and adversarial probing, though we found that participants largely perceived these measures as ineffective. We outline implications including implementing institution-level sandboxed isolation, scenario-based privacy pedagogy, and verifiable data-deletion audits for transparency.

cs.HC↗

arXiv2026

SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative Workflow

The intricate nature of modern surgical care necessitates intelligent systems that can synthesize extensive patient records, support collaborative decision-making, and provide transparent, auditable reasoning across the entire perioperative workflow. Although web-based Large Language Models (LLMs) possess advanced reasoning capabilities, they are ill-equipped for surgical applications due to critical limitations: input length constraints, incomplete memory management, and limited traceability. To address this issue, we present SURGENT, a surgical multi-agent assistance system that combines a Tree-of-Thought planner, multi-department collaboration agents, and retrieval-augmented reasoning with clinical guidelines and biomedical literature. SURGENT features a novel memory design that manages both long-term patient histories and short-term working summaries, enabling more complete, contextualized, and consistent reasoning. Experimental evaluations across five key perioperative tasks - case analysis, surgical plan simulation, safety monitoring, complication risk assessment, and rehabilitation guidance - show that SURGENT outperforms baseline LLMs and existing medical multi-agent frameworks, yielding recommendations more closely aligned with patient histories. Ablation studies further highlight the advantage of DeepSeek as a locally deployable backbone model, enabling privacy-preserving deployment without reliance on centralized services. These results position SURGENT as a practical and trustworthy advancement toward intelligent, equitable, and secure surgical assistance systems.

cs.CL↗

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↗

arXiv2026

Electrically tunable circular photocurrent via local-field induced symmetry breaking at a metal-MoTe2 interface

Transition metal dichalcogenides (TMDCs) constitute a promising platform for symmetry-engineered responses to circularly polarized light. The high crystal symmetry of centrosymmetric 2H-phase TMDCs inherently forbids the circular photogalvanic effect, thereby necessitating external stimuli such as electric fields or strain to lower the symmetry for its activation. While Schottky junctions provide a ubiquitous built-in field for potentially inducing circular photocurrents, the mechanism for the generation and control of circular photocurrents in TMDCs is not understood. In this study, we fabricated a localized gold-MoTe2 heterostructure and demonstrate a pronounced circular photocurrent at the interface under normal incidence. The photocurrent is attributed to circular photogalvanic effect governed by the strength and direction of the built-in electric field, enabling continuous modulation via an external bias. First-principles calculations show that the gold interface induces a spin splitting in the valence bands of MoTe2, establishing a valley-dependent spin ordering. The observed circular photocurrent from multilayer 2H-MoTe2 under normal incidence indicates the breaking of C3 rotational symmetry by the local in-plane field. These results establish an effective strategy for developing voltage-tunable circularly polarized photodetectors and valleytronic devices.

cond-mat.mtrl-sci↗

arXiv2026

Roomify: Spatially-Grounded Style Transformation for Immersive Virtual Environments

We present Roomify, a spatially-grounded transformation system that generates themed virtual environments anchored to users' physical rooms while maintaining spatial structure and functional semantics. Current VR approaches face a fundamental trade-off: full immersion sacrifices spatial awareness, while passthrough solutions break presence. Roomify addresses this through spatially-grounded transformation - treating physical spaces as "spatial containers" that preserve key functional and geometric properties of furniture while enabling radical stylistic changes. Our pipeline combines in-situ 3D scene understanding, AI-driven spatial reasoning, and style-aware generation to create personalized virtual environments grounded in physical reality. We introduce a cross-reality authoring tool enabling fine-grained user control through MR editing and VR preview workflows. Two user studies validate our approach: one with 18 VR users demonstrates a 63% improvement in presence over passthrough and 26% over fully virtual baselines while maintaining spatial awareness; another with 8 design professionals confirms the system's creative expressiveness (scene quality: 5.95/7; creativity support: 6.08/7) and professional workflow value across diverse environments.

cs.HC↗

arXiv2026

Mind the Gap: Mapping Wearer-Bystander Privacy Tensions and Context-Adaptive Pathways for Camera Glasses

Camera glasses create fundamental privacy tensions between wearers seeking recording functionality and bystanders concerned about unauthorized surveillance. We present a systematic multi-stakeholder evaluation of privacy mechanisms through surveys (N=525) and paired interviews (N=20) in China. Study 1 quantifies expectation-willingness gaps: bystanders consistently demand stronger information transparency and protective measures than wearers will provide, with disparities intensifying in sensitive contexts where 65-90% of bystanders would take defensive action. Study 2 evaluates twelve privacy-enhancing technologies, revealing four fundamental trade-offs that undermine current approaches: visibility versus disruption, empowerment versus burden, protection versus agency, and accountability versus exposure. These gaps reflect structural incompatibilities rather than inadequate goodwill, with context emerging as the primary determinant of privacy acceptability. We propose context-adaptive pathways that dynamically adjust protection strategies: minimal-friction visibility in public spaces, structured negotiation in semi-public environments, and automatic protection in sensitive contexts. Our findings contribute a diagnostic framework for evaluating privacy mechanisms and implications for context-aware design in ubiquitous sensing.

cs.HC↗

arXiv2026

Request a Note: How the Request Function Shapes X's Community Notes System

X's Community Notes is a crowdsourced fact-checking system. To improve its scalability, X introduced ``Request Community Note'' feature, enabling users to solicit fact-checks from contributors on specific posts. Yet, its implications for the system -- what gets checked, by whom, and with what quality -- remain unclear. Using 98,685 requested posts and their associated notes, we evaluate how requests shape the Community Notes system. We find that requested posts with higher GPT-estimated misleadingness and from authors with greater misinformation exposure are more likely to receive notes. Conversely, requested political posts (vs. non-political) are less likely to receive notes. We also observe partisan asymmetries: posts from Republicans are more likely to receive notes than those from Democrats. Although only 12% of requested posts receive request-fostered notes from top contributors, these notes are rated as more helpful and less polarized than others, partly reflecting top contributors' selective fact-checking of misleading posts. Our findings highlight both the limitations and promise of requests for scaling high-quality community-based fact-checking.

cs.SI↗