跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1284新增论文
+1011其中 AI 相关
+150已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 10:50各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 12:16 — 2026-11-20 12:16(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 10:50库内论文最新更新时间:2026-11-19 12:39

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,155 已收录论文23,386 AI 相关8,624 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 644 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.20713

Injectra: Retrofitting Extensibility into Web-Based Desktop Applications

Qin Sun

原文摘要

Large language models can generate code based on natural language prompts, opening up new possibilities for users to customize software and extend its functionality. This paper proposes and implements Injectra, a general-purpose code injection and feature enhancement system for existing desktop clients, suitable for applications whose user interfaces are built using embedded browser engines (such as Electron) or system WebViews (such as Tauri). Injectra decouples the host integration logic from the upper-layer enhancement code. Combining both runtime integration and pre-launch bootstrap mechanisms, it injects JavaScript, HTML, and CSS into the application's internal Web runtime environment through a unified execution channel, thereby enabling modifications to interface rendering, adjustments to interactive behaviors, and client-side functionality extensions. The system uses a command-line interface (CLI) as a unified entry point, allowing external tools, AI agents, and MCP integration layers to reuse its injection and enhancement capabilities. We tested 38 desktop applications already installed on our macOS machine; code injection was successfully completed for all of them. We demonstrated the system's capability to extend functionality through various enhanced use cases and also successfully validated the Windows version. Based on Injectra, we further developed an LLM-powered enhancement tool driven by selection and annotation: users select interface objects within the original application and describe their modification requirements; the large language model then generates the enhancement code, which is injected, executed, and rendered by Injectra. The system's source code has now been released as open source: https://github.com/sqmw/injectra.

cs.SE · cs.HC

版本更新 · v2arXiv:2609.17355

Evaluating Ambient Clinical Scribes in India: The Need for Multilingual Real-World Clinical Conversation Data

Siddharth D Jaiswal, Krithi Shailya, Ashish Makani, Suvrankar Datta, Sunayana Sitaram, Mohit Jain

原文摘要

Ambient clinical scribes (ACS) are being rapidly deployed at scale across Global South healthcare settings to reduce clinicians' documentation time, especially in overburdened environments such as India. These ACS are primarily developed or distilled from models built and validated on Global North speech, languages and consultation styles. Indian clinical encounters are brief, triadic, multilingual, code-mixed with low-resource languages, and conducted in highly resource-constrained, noisy settings -- increasing the likelihood of ASR and note-generation errors manyfold. We argue for a standardized evaluation infrastructure to assess whether these systems are safe, reliable, and well-suited to the Indian healthcare setting. We substantiate our claims through a mixed-methods study -- a systematic survey of publicly available patient-clinician conversational datasets, a quantitative comparison of some simulated datasets against conversational and cultural markers drawn from the Indian clinical-communication literature, and semi-structured interviews with four organizations building and deploying ACS in India. Our survey shows that there are no large-scale, publicly available, real-world benchmarks for ACS in India, with existing datasets being overwhelmingly synthetic or simulated. We note that amongst the available simulated datasets that we compare, the Global North datasets diverge significantly from the expected conversational and cultural structures of their Indian encounters. Finally, our interviews reveal that deploying organizations have each built proprietary, incomparable evaluation pipelines, creating a fragmented ecosystem with no independent and reliable basis for procurement. We call for the development of a publicly shared, real-world, multilingual benchmark for ACS evaluation and outline the properties and policies such a benchmark would require.

cs.CY · cs.HC

版本更新 · v2arXiv:2606.18692

Text-Based Visualizations for Learning Analytics: Perspectives from STEM Education Researchers

Huyen N. Nguyen, Kathleen Bowe, Minh-Huyen Nguyen, Kit Thompson, Caleb M. Trujillo

原文摘要

Visualizing student reflections collected throughout a course can help instructors track changes in student language and inform teaching decisions. Interpreting these changes, however, requires tools that connect overall patterns with individual responses, and how to design such visualizations for learning analytics remains an open question. To address this gap, we conducted a mixed-methods study with 10 STEM education researchers who offered dual perspectives as both instructors and qualitative researchers. We used two visualization platforms as probes to elicit expert perspectives: the Journal Data Dashboard, for analyzing formative assessments, and WordStream Maker, for authoring custom visualizations. Participants evaluated both platforms by analyzing weekly student journal responses from a data visualization course. Findings revealed shared prioritization of context and control, discipline-rooted differences in perceived usefulness, and, notably, epistemological disagreement about frequency as viable evidence in qualitative work. Some participants regarded frequency-based visualization as a productive entry point to qualitative analysis, while others argued that it conflicts with the values of qualitative data analysis and may obscure rare but critical responses. These findings support the argument that perceived ease of use and usefulness, context of use or role, and epistemic frames are relevant to users of qualitative data visualization and learning analytics tools. We discuss design implications for future tools to better integrate quantitative techniques with qualitative interpretation. Transcripts, tutorials, and all supplementary materials are available at https://osf.io/z2f8d.

cs.CY · cs.HC

新论文 · v1arXiv:2611.20612

Learning Design Taste through Verifiable Synthetic Environments and Agentic Reinforcement Learning

Sujay choubey, Siddhant Saxena, Sarthak Kapil, Suhas Motwani

原文摘要

Code-generating language models produce user interfaces that build and run, but the pages are often weak in hierarchy, spacing, typography and composition. We study whether a small code model can learn design taste through reinforcement learning in verifiable synthetic environments. The method has three components. First, a layered verification framework splits design quality into hard gates, render-grounded metrics, rubric judges, within-group relative preference and a blinded expert panel. A signal enters the reward only if it passes an admission protocol that tests agreement with experts, causal sensitivity, resistance to hack traps and stability. Second, following SCALER [1], synthetic design environments are parameterised generators with measured difficulty ladders: base pages are written once by an agentic coder, and instances are produced by syntax-tree perturbation operators and constraint samplers, scheduled by an adaptive curriculum with a quarantine rule against reward over-optimisation. Third, a 4B code model is trained with agentic reinforcement learning over multi-turn episodes in which it edits and builds a repository and reads a textual report of its own render, while hidden graders compute the reward. The admission protocol admits 7 of 16 render signals and 6 of 10 rubric dimensions. On TD-Bench, agentic training raises the Taste Index from 0.630 to 0.795 in-family and from 0.598 to 0.700 on held-out families, and wins 0.600 of blinded expert comparisons against the base model and 0.569 against a single-turn control. Most of the advantage depends on the inference-time loop, and cross-brief distinctiveness falls slightly below that of the base model, the only success criterion not met.

cs.MA · cs.HC

版本更新 · v4arXiv:2606.08281

Toward Interaction Dynamics: A Predictive Framework for Safe Physical Human Robot Interaction

Yongyan Cao, Jinshan Tang

原文摘要

Physical human-robot interaction requires yielding transiently to contact yet recovering the commanded reference under sustained load. Finite-stiffness impedance control retains a static deflection there, while predictive alternatives typically optimize a nonlinear model online. Operational-space cancellation instead exposes a translational error double integrator with a fixed transition matrix and a configuration-scheduled input map, making interaction a predictive quantity. We build on it a compact offset-free interaction-error MPC for torque-controlled manipulators: a force-domain random-walk state estimates persistent interaction and model error, and a 30-variable convex QP maps the correction through the current task inertia while constraining the applied joint torque. Conditional results establish impedance equivalence of the unconstrained passive feedback, offset-free regulation at feasible frozen configurations, and quadratic stabilizability of the scheduled backbone. In a 1 kHz MuJoCo simulation of a 7-DOF Franka FR3, the estimator cuts steady-state error under a repeated 15 N step from 2.73 mm to 0.033 mm when added to the otherwise identical 100 Hz MPC, at unchanged peak joint power. A stiffness-and-damping-calibrated impedance baseline attains 2.63 mm at the same actuator cost, and 1.36 mm with ideal measured-force cancellation, so constant-load rejection is not unique to MPC; the sensorless controller still reaches 0.033 mm. The torque constraint holds the command inside a budget tightened to the lowest the task can meet, at no tracking cost. On a physical UR5e, five alternated pairs under a nominal 1.5 kg hanging load give 1.505 mm without the estimator; with it the controller is offset-free, its 0.023 mm error being the noise level of the encoder-based position measurement. A tuned anti-windup integral also removes the offset, with larger transients.

cs.RO · cs.HC · eess.SY · physics.med-ph

版本更新 · v3arXiv:2609.34655

AI Tools Adoption across the Double Diamond Workflow: Phase, Mode, and Barriers in Designer Practice

Sepideh Tajarmakan, Khashayar Hojjati Emami

原文摘要

Designers are adopting AI faster than the tools built for them can keep up. General-purpose conversational AI led AI use among designers in three of the four phases of design work, ahead of tools built for design. We surveyed 443 designers from at least 43 countries about AI use in each phase of the Double Diamond: Discover, Define, Develop and Deliver. Tools were classified by output and function. Of these designers, 79.7% confirmed AI use in at least one phase. Adopters used AI in a mean of 2.89 phases, and only 35.1% used it in all four. They added phases in workflow order, from Discover onward. Conversational tools led in Discover, Define and Deliver. AI-native image generation led in Develop, where AI-native tools peaked at 57.6% of tool picks. Embedded AI features in existing design software peaked later, in Deliver (37.5%). Fewer designers used AI in later phases, from 318 in Discover to 182 in Deliver. Those who did named a similar number of tools per phase. Low perceived usefulness was the only barrier that separated non-adopters (40.5%) from adopters (16.4%) after correction for multiple tests. Concern about accuracy was similar in both groups.

cs.HC

新论文 · v1arXiv:2611.20519

AI Tool Adoption and Loyalty among Product, Industrial, and UX/UI Designers across the Double Diamond

Sepideh Tajarmakan, Khashayar Hojjati Emami

原文摘要

Designers share many AI tools, yet their roles produce different work. This survey compared 337 Product, Industrial and UX/UI Designers from 40 countries and regions across the four phases of the Double Diamond. It measured AI adoption, breadth and frequency, tool function and the number of tools named per phase. A tool was loyal when a role picked it in all four phases. Industrial Designers adopted AI less often (73.9% against 88.2% and 87.9%), a gap that went with physical projects once project type and country were held constant. Of 60 AI tools, 25 were common to all three roles and carried at least 90% of each role's picks. Tool function differed by role, most of all in Develop. A few loyal tools carried about half of the picks, led by ChatGPT. Tool counts fell across the phases in every role. A hurdle model found a Phase x Role interaction for using AI in a phase (p = 0.041), which was not shown for the number of tools (p = 0.080). Predicted adoption among UX/UI Designers fell from 87.2% in Define to 43.9% in Develop. Support for designers needs one shared core, role-specific tools and most attention in Develop.

cs.HC

版本更新 · v2arXiv:2603.27928

Generalizable Social Bot Detection via Multi-Granularity Summarization and Domain-Invariant Learning

Boyu Qiao, Zixin Tang, Yunman Chen, Xiaoshuai Hao, Dongyu She, Wei Zhou, Yunfeng Diao, Songlin Hu

原文摘要

Social bots are becoming increasingly sophisticated in mimicking human users, posing persistent threats to online information ecosystems. Despite substantial progress in social bot detection, existing methods often generalize poorly to unseen datasets. Two challenges underlie this limitation: heterogeneous user information across datasets makes consistent representation difficult, while distribution shifts encourage reliance on domain-specific patterns. To address these challenges, we propose Multi-Granularity Summarization and Domain-Invariant Learning (MGDIL), a unified framework for generalizable social bot detection. MGDIL first converts profile attributes into structured textual descriptions and summarizes historical posts into user-level behavioral representations, providing a shared semantic interface across heterogeneous datasets. It then combines task-oriented instruction tuning, domain-adversarial learning, and cross-domain contrastive learning to reduce dependence on domain-specific patterns while preserving discriminative information between bots and human users. We construct a unified instruction-tuning corpus from 15 social bot datasets, train MGDIL on 13 earlier datasets, and evaluate it on two later-collected unseen datasets under a temporally ordered cross-dataset protocol. Comparisons with representative conventional, neural, LLM-based, and transfer-based baselines, together with ablation and representation analyses, demonstrate the effectiveness of MGDIL in improving generalization across datasets. The code is available at: https://github.com/QQQQQQBY/MGDIL.

cs.SI · cs.HC

版本更新 · v3arXiv:2603.02578

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities

Ziwen Xu, Kewei Xu, Haoming Xu, Haiwen Hong, Longtao Huang, Hui Xue, Ningyu Zhang, Yongliang Shen 等 11 位作者

原文摘要

Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality, pose significant risks. We introduce SteerEval, a hierarchical benchmark for evaluating LLM controllability across three domains: language features, sentiment, and personality. Each domain is structured into three specification levels: L1 (what to express), L2 (how to express), and L3 (how to instantiate), connecting high-level behavioral intent to concrete textual output. Using SteerEval, we systematically evaluate contemporary steering methods, revealing that control often degrades at finer-grained levels. Our benchmark offers a principled and interpretable framework for safe and controllable LLM behavior, serving as a foundation for future research.

cs.CL · cs.AI · cs.HC · cs.LG

新论文 · v1arXiv:2611.20488

EVIDENT: Evaluating Evidence Grounding in GUI Agents

Yerin Nam, Minkyung Cho, MinKyu Kim, SeungWoo Song, Hangyeol Yoo, Jihyo Kim, KyungTae Lim

原文摘要

GUI agents are increasingly evaluated by whether they complete web tasks, but surface success can hide a critical failure: the final answer may not be supported by evidence observed during navigation. We introduce EVIDENT, an evidence-driven benchmark for evaluating whether GUI agents ground their decisions in observable web evidence. EVIDENT contains 220 real-world English and Korean tasks spanning semantic grounding, contextual inference, and visual grounding, each paired with human-curated evidence metadata specifying what must be verified. We further separate surface task completion from evidence-grounded success using three metrics: TSR, ESR, and GSR, which respectively measure outcome success, required evidence observation, and claim-level evidence support. Experiments on commercial and open-source GUI agents reveal substantial gaps between surface success and evidence-grounded success, especially in contextual and visual tasks. These results show that current evaluations can overestimate agent reliability and highlight the need to assess not only whether agents answer, but whether they verify.

cs.AI · cs.HC

新论文 · v1arXiv:2611.20485

PromptPoseFX: Authoring Pose-Driven Visual Effects through Augmented Prompting and Interactive Refinement

Kexin Zheng, Hui Ye, Hongbo Fu

原文摘要

Human pose-driven visual effects offer a compelling way for enhancing video expressiveness and storytelling. Authoring such effects with traditional video editing tools is a complex and time-consuming task that requires considerable technical expertise and manual effort. While generative AI models can simplify the workflow by reducing manual scripting through language-driven generation, existing approaches suffer from imprecise alignment between visual effects and pose data, failure to preserve original video content, and limited support for fine-grained, iterative refinement. To address these challenges, we present PromptPoseFX, an interactive system that allows creators to author pose-driven visual effects through augmented language prompts and interactive refinement. Our system leverages Large Language Models (LLMs) to translate high-level user intent into parameterized procedural graphics scripts, automatically mapping pose-tracking data to specific effect parameters, allowing precise alignment with human motion. This script-based approach manages effects as independent layers, thereby preserving the original content of the underlying video. To reduce language ambiguity, our interface offers controls across spatial, temporal, and parameter domains, enabling the precise, intuitive, and iterative authoring of pose-driven visual effects. We evaluated PromptPoseFX through a comparative study against a text-only LLM interface, followed by an exploratory study. In the comparative study, participants rated PromptPoseFX significantly higher than the text-only baseline on measures of perceived control and precision. The exploratory study examined usability and creativity support in open-ended authoring tasks.

cs.HC

版本更新 · v2arXiv:2411.04542

Towards Identification of Political Posts in Social Media Text Using Deep Learning Models

Sultan Ahmed, Salman Rakin, Md. Mostofa Akbar

原文摘要

The increasing growth of social media provides us with an instant opportunity to be informed of the opinions of a large number of politically active individuals in real-time. We can get an overall idea of the text nature of these individuals on governmental issues by analyzing the social media texts. Nowadays, different kinds of news websites and popular social media such as Facebook, YouTube, Instagram, etc. are the most popular means of communication for the mass population. So the political perception of the users toward different parties in the country is reflected in the data collected from these social sites. In this work, we have extracted three types of features, such as the stylometric feature, the word-embedding feature, and the TF-IDF feature from the text and applied different kinds of machine learning models including deep learning models. Finally, the deep learning models are compared against traditional machine learning classifiers during identification of political nature from the text. We have compared our methodology with the research work in different languages. Among them, the word embedding feature with LSTM outperforms all other models with 88.28\% accuracy.

cs.HC

新论文 · v1arXiv:2611.20378

Straight to the Product: What Online Retailers Miss When Shoppers Ask AI First

Michael Iannelli, Alan Ai

原文摘要

When people ask an AI assistant what to buy, what happens next at the store? We link the same people's assistant conversations to their later browsing at twenty large online retailers. People go to the product the assistant named: among shoppers who had not visited the store in the past week, visits to the named product within a day rise from 0.02 to 2.07 per 100 answers (+2.0 points [1.7, 2.4]), and on days with a product-page visit at the store, 44% show a product from their own answer, against 1.5% for a matched answer given to someone else. The result replicates in a separate five-month period. Few arrive through the assistant's link: 89% of visits carry no sign of it, and 54% follow a web search, the same share as their usual visits. When a search comes just before the first visit, it names the answer's product 28% of the time (1% in earlier weeks), as if the search box were an address bar. The chat names the product; the store logs a search. Once there, shoppers keep browsing. We propose product follow-through, the share of answers followed by a visit to the product they named, as a way to evaluate shopping assistants and agents by what people do next: it needs no referral data or provider logs and can be computed for each assistant.

cs.IR · cs.CY · cs.HC

新论文 · v1arXiv:2611.20375

Supporting Community Members Navigating Reentry with Revisable Future Envisioning

Modhumonty Das, Nathan Morelli, Aakash Gautam

原文摘要

Future-planning tools often treat agency as individual and leave out the institutional conditions that shape how aspirations become action. We examine this tension in the context of reentry from incarceration and recovery from substance use disorder, through a partnership with a nonprofit organization. Building on participants' physical vision-board practices, we designed a digital future-envisioning tool that helps users represent current circumstances, desired futures, and pathways that connect goals to concrete resources. We draw on data from three workshops involving 18 participants and follow-up interviews with 10 participants to examine how they used future envisioning within a fragmented support system. Participants described reentry and recovery as ongoing processes in which the everyday work of staying stable was central to progress. Envisioning futures supported this work by surfacing constraints and interdependencies, by reframing personal strengths and institutional supports as assets, and by helping participants move from abstract hopes toward articulated goals and contingent plans. We theorize revision as maintenance work and conclude with design implications for community-embedded interactive systems that support revisable, dependency-aware planning.

cs.HC · cs.CY

新论文 · v1arXiv:2611.20367

"Can a Robot Really Care About Me?" How Perceiving a Tutor as Human or AI Affects Computer Science Students' Attitudes and Experiences

Tymon Vu, Wenxuan "Wendy" Shi, Silas Hsu

原文摘要

Conversational artificial intelligence can reproduce many instructional and social behaviors of human tutors, but students may interpret those behaviors differently depending on who they believe is providing them. We examined how perceived tutor identity shapes students' evaluations of instructional feedback, satisfaction of psychological needs according to Self-Determination Theory, and their communication strategies with tutors. In a within-subjects Wizard-of-Oz study, 27 introductory computer science students completed two text-based tutoring sessions involving Python code-explanation problems. Participants were told one tutor was human and the other was AI, although the same human provided feedback in both conditions. We found participants evaluated both tutors favorably and reported few consistent differences in the instructional value of the feedback. However, participants frequently questioned whether AI could genuinely care about them, which corresponded with the human tutor having higher scores of relatedness need satisfaction. Human presence offered connection and accountability for some participants but introduced anxiety in others. Participants also reported communicating more casually with the human tutor and more explicitly with the AI tutor. These findings suggest complementary roles for human and AI tutoring and highlight the importance of considering psychological needs alongside instructional quality.

cs.HC

新论文 · v1arXiv:2611.20330

Sidewalk Stewards: A Visual Analytics Approach for Interactive Topology Repair of Sidewalk Networks

Stefan Cobeli, Leonardo Ferreira, Logan Loch, Luiza Melo, Peyman Baghershahi, Claudio D. G. Linhares, Nivan Ferreira, Sourav Medya 等 10 位作者

原文摘要

Accurate pedestrian network data is foundational to urban accessibility, routing, and infrastructure planning, yet such data remains scarce and difficult to produce at scale. Automated extraction pipelines have made significant strides by leveraging computer vision to derive sidewalk networks from aerial imagery, and have seen real-world adoption by municipalities seeking cost-effective inventory solutions. Yet, these pipelines consistently produce topological errors (e.g., disconnected components, dangling edges, missed connections, malformed intersections) that undermine the utility of the extracted networks for routing and accessibility analysis. Correcting these errors requires situated human judgment that global automated repair strategies cannot replicate, yet practitioners currently lack dedicated tools to support this work efficiently. We present Sidewalk Stewards, a visual analytics system that bridges the gap between automated extraction and a deployment-ready pedestrian network. Sidewalk Stewards detects candidate topology errors, supports interactive user-guided correction through coordinated spatial views, and provides real-time quality feedback as edits are applied. We evaluate Sidewalk Stewards through a comparative user study, case studies across cities, and a quantitative evaluation. Compared with conventional workflows, the system facilitates error identification and enables faster and more complete correction. The case studies illustrate the workflow across different urban contexts, and the quantitative evaluation shows that a small number of user corrections can enhance multiple sidewalk quality metrics. Sidewalk Stewards is available at urbantk.org/sidewalk.

cs.HC · cs.CV · cs.CY

新论文 · v1arXiv:2611.20315

Vibe Interventions: Can Users Personalize and Iterate Their Way to Behavior Change?

Sally Ahmed, Ayse Alomar, Tawab Safi, Pattie Maes, Pat Pataranutaporn

原文摘要

Recent advances in large language models allow a working application to be generated from natural-language description, and is referred to as generative user interfaces. Their application to behavior change is unexplored, and we provide one of the first controlled investigations of it. We distinguish two components of authorship: iteration, the revision of a generated artifact in natural language, and personalization, the conditioning of generation on stated context. In a pre-registered between-subjects experiment (N = 300, 60 per condition), we crossed these two factors and added a static intervention as a control, yielding five conditions; participants stated a goal and received a generated intervention. The personalized generative condition ranked highest on every self-report outcome, including ownership, satisfaction, and intended adoption. Randomized iteration had no detectable effect, and higher revision counts were negatively associated with evaluative ratings. This work establishes which component of authorship carries motivational value in generative behavior change tools.

cs.HC

新论文 · v1arXiv:2611.20311

Reveal: A Provenance-Aware System for Multimodal Urban Data Exploration

Leonardo Ferreira, Joao Rulff, Maryam Hosseini, Aline Paes, Daniel de Oliveira, Fabio Miranda, Marcos Lage

原文摘要

Urban sensing initiatives increasingly produce multimodal datasets that combine visual and textual information to capture city characteristics and subjective factors such as safety, comfort, and accessibility. Yet, analyzing such data at scale remains difficult, as manual inspection is unfeasible and automated methods struggle to interpret subjective cues and uncover relationships across diverse data modalities. Moreover, existing workflows rarely make exploration steps explicit, hindering reproducibility. To address these challenges, we introduce Reveal, a provenance-aware visual analytics system for exploring heterogeneous urban data. Reveal enables users to build dataflows by combining text and image searches across coordinated views, chaining queries into pipelines, and applying set operations within an exploration diagram while capturing analytical provenance. We evaluate Reveal through two case studies focused on accessibility and walkability.

cs.HC · cs.CY · cs.MM

新论文 · v1arXiv:2611.20245

From XR Sketches to CAD: Preserving Design Intent with AI

Trudi Di Qi

原文摘要

Extended reality (XR) allows designers to sketch shapes directly in 3D, but converting these sketches into editable, feature-based CAD requires interpreting their intent. A sketch may contain drawing errors, intended features, and design choices that remain open. Correcting every irregularity risks erasing intended features, while automatic completion may impose choices the designer has not made. We argue that AI should add precision without overriding design intent, considering both the resulting shape and how the CAD model behaves during later edits. To guide this process, we propose a conceptual framework that distinguishes errors from intentions in individual sketch properties and relates them to correction, preservation, and exploration in editable CAD. We also outline five research directions for sketch interpretation, CAD construction, and evaluation, with testable hypotheses for selected questions.

cs.HC · cs.GR

版本更新 · v3arXiv:2604.03237

Supporting Calibrated Reliance in AI-Assisted Decision-Making: Different Strategies for Different Tasks

Ruth Cohen, Lu Feng, Ayala Bloch, Sarit Kraus

原文摘要

As AI systems increasingly support human decision-making, a central challenge is determining what information helps people recognize when to rely on AI predictions and when to question or override them. Across three controlled human-subject studies spanning abstract visual reasoning with RAVEN matrices and deductive logical reasoning with LSAT problems, we examine how different forms of AI support affect performance in AI-assisted decision-making. A multi-stage reveal study shows that AI predictions and explanations can affect objective accuracy and subjective confidence differently. In visual reasoning, LLM explanations do not improve accuracy beyond the predicted answer alone, and no additional support format significantly outperforms prediction-only support; predicted probabilities show the highest descriptive accuracy and error recovery, while a derived selective-automation policy provides a higher-performing reference benchmark. In language-based logical reasoning, by contrast, LLM explanations yield the highest accuracy and error recovery, outperforming expert-written explanations and probability-based support. These results suggest that the effectiveness of AI support strategies depends on the task setting. Human--AI interfaces should instead be designed to support calibrated reliance and effective error recovery by matching the form of assistance to the task and the evidence available to users.

cs.HC · cs.AI · cs.CL

新论文 · v1arXiv:2611.20196

DoF-Query Transformer for Adaptive Fusion of Egocentric Vision and Forearm HD-sEMG in Continuous Hand Kinematics

Jiahang Liu, Wenbo Zhang, Junsong Wang, Zhenzhi Ying, Siqi Hou, Naohiko Sugita, Liming Shu

原文摘要

Continuous and accurate estimation of human hand kinematics is important not only for intuitive human-machine interaction, but also for capturing fine-grained human manipulation demonstrations that can provide action supervision for embodied-intelligence datasets and dexterous robot learning. However, individual sensing modalities may be insufficient for reliable estimation under varying operating conditions. We present a finger-unencumbered multimodal framework for continuous regression of 20 hand joint angles from egocentric RGB images and 128-channel forearm high-density surface electromyography (HD-sEMG). The framework combines a Vision Transformer-based visual encoder, a Transformer-based EMG encoder, and a degree of freedom (DoF) query Transformer fusion decoder. To account for the varying informativeness of visual and EMG cues across joint DoFs and input conditions, the decoder assigns a separate learnable query to each DoF, enabling DoF-specific and context-adaptive fusion of the two modalities. The framework was evaluated on synchronized multimodal data from 10 participants. Averaged across participants, the proposed fusion model achieved a mean coefficient of determination ($R^2$) of $0.88$ and a mean absolute error (MAE) of $2.80^\circ$, compared with $0.82$ and $3.21^\circ$ for the vision-only model and $0.68$ and $5.13^\circ$ for the EMG-only model. It also outperformed the evaluated representative unimodal baselines and alternative fusion designs. DoF-wise analyses showed larger fusion gains for visually ambiguous joints and viewing conditions, while synthetic visual occlusion demonstrated greater robustness than vision-only estimation. These results highlight the complementary value of egocentric vision and forearm HD-sEMG for capturing fine-grained human hand kinematics, with potential applications in human demonstration acquisition and dexterous robot learning.

cs.CV · cs.HC · cs.LG

新论文 · v1arXiv:2611.20190

A Line is Not Just a Line: Visualizing Harmonious Complex Line Sets

Francesca Samsel, Daniel F. Keefe, Gregory Abram

原文摘要

Line is a foundational building block in visual design for traditional media and computer graphics. Controlled variation in line quality can be used to define form, create abstractions, distinguish categories, control affect, and more. Yet, when it comes to computer graphics visualizations of science, particularly those built upon 3D computer graphics, too often a line is just a line. This portfolio presents a series of visual design studies and lessons learned that explore the diverse character of line that might be useful for 3D visualizations. The imagery begins to show how more sophisticated use of this powerful visual building block could increase the clarity of data visualizations while also bringing a human, handcrafted aesthetic that reinforces the people and impacts behind scientific climate data.

cs.HC · cs.GR

新论文 · v1arXiv:2611.20187

Cyber-Secure Wearable, Ultra-Low-Power Networked Sensors for Soldier Health Monitoring: Insights from the CAPSARII project

Luciano Bozzi, Christian Celidonio, Umberto Nuzzi, Massimo Biagini, Stefano Cherubin, Asbjørn Djupdal, Tor Andre Haugdahl, Andrea Aliverti 等 22 位作者

原文摘要

The CAPSARII project advances a cyber-secure, ultra-low-power wearable platform and Internet of Battlefield Things (IoBT) framework to support real-time monitoring of military personnel and data-driven decision support. The architecture integrates smart-textile sensing, a body/squad area mesh, edge-deployed AI on secure RISC-V microcontrollers, and cloud/federated analytics for cross-mission learning and comparative studies. Two representative use cases--pilot fatigue and warfighters operating in harsh environments--guide requirements, validation, and interface design (including HUD and haptic feedback). As an initial step toward embedded models, we benchmark stress classification on a public wearable dataset: tree-ensemble baselines achieve state-of-the-art performance for accuracy and F1 (e.g., XGBoost: $\mathrm{Accuracy}=0.901\!\pm\!0.023$, $\mathrm{F1}=0.920\!\pm\!0.019$), while a feature-based Transformer attains the highest AUC ($0.963\!\pm\!0.025$), informing feature-engineering and compression choices for edge deployment. Building on these results, CAPSARII employs HW/SW co-design, model compression (pruning, quantization, distillation), and precision tuning to meet stringent energy and memory budgets; it further investigates Processing-in-Memory accelerators for future efficiency gains. A structured gap analysis highlights the remaining challenges: establishing validation standards for physiological signal quality and textile durability; achieving low-latency, scalable BAN/SAN communications under mobility and interference; and deploying hybrid lightweight/post-quantum cryptography with robust device identity and side-channel resilience on constrained endpoints. By consolidating these elements into a coherent, secure IoBT stack, CAPSARII delineates a practical roadmap from laboratory baselines to mission-ready soldier monitoring in both training and operational scenarios.

cs.ET · cs.AI · cs.AR · cs.CR · cs.HC · cs.LG

新论文 · v1arXiv:2611.20083

WL-Headset Law: Projecting Future Headset Evolution from a Decade of Display and Mass Data

Jialin Wang, Hai-Ning Liang

原文摘要

Tracking a decade of headset display and mass changes can inform forecasts. However, comparing headset resolution requires pixels per degree (PPD), which is often unreported and estimated using unclear assumptions. Therefore, we compile the open-source, evidence-linked HMD Resolution and Mass Database (HRMD) with 241 configurations from 2016--2026 and introduce structure- and axis-aware robust calibration (SARC) to estimate missing central PPD. Compared with official PPD, SARC reduces PPD estimation error from 14.8% for traditional geometric estimation to 3.2%. Based on HRMD, we introduce the Weight-Linked Headset Law (WL-Headset Law), which models PPD by year, mass, and category. The law reveals 7.4% annual PPD growth at fixed mass and category. Meanwhile, head-worn mass fell by 6.5% annually after category adjustment. At an eyeglass-like mass of 30g, the law projects average central PPD of 60 (normal visual acuity) around 2035 and 120 (higher acuity) around 2044 if trends persist.

cs.HC

版本更新 · v2arXiv:2606.12585

Revisiting the ABCs of Working with AI: Evidence from Radiologists

Daniel Martin

原文摘要

I examine the relationship between the benefits of working with AI and two baseline traits - ability and belief calibration - among all 227 radiologists available in Collab-CXR, a dataset from an experiment where AI assistance was provided during X-ray diagnosis. When analyzed jointly, both lower unassisted accuracy and smaller miscalibration, measured by the absolute gap between average confidence and accuracy, are associated with greater improvements in accuracy with AI. In addition, the association between unassisted accuracy and improvement with AI becomes more negative and statistically significant when controlling for calibration.

econ.GN · cs.HC

新论文 · v1arXiv:2611.20061

Turning Errors into Successes: Designing LLM Tutoring Around Scaffolded Error Correction

Michael W. Asher, Meng Cao, Paulo F. Carvalho

原文摘要

Large language models (LLMs) could make personalized tutoring available at scale, but it remains unclear how they can best support the instructional processes that make one-on-one instruction effective. We compared two ways of using LLMs after students make errors: providing personalized explanations of those errors, or engaging students in additional cycles of scaffolded practice and feedback, with a Socratic tutor guiding students toward the correct answer. In a preregistered online experiment, 400 adults practiced setting up constraint equations and, after each attempt, received the correct answer, a generic explanation, a personalized LLM explanation of their error, or Socratic tutoring. Socratic tutoring helped: participants resolved 64% of their errors through the dialogue and scored 0.24 SD higher on practice-aligned posttest questions than those who received generic or personalized explanations. Socratic participants also found the session more interesting, less frustrating, and less costly, even though it took nearly twice as long. In contrast, we found no evidence of a benefit of personalized explanations over generic ones, and neither type of explanation reliably outperformed simply seeing the correct answer. These findings suggest that LLM tutors may add the most value not by explaining errors more precisely but by helping students correct those errors themselves through scaffolded practice. This pattern fits a mastery-experience account of tutoring, in which an effective tutor notices when a student is struggling, steps in with guidance, and works with the student until the struggle resolves into success. AI tutors may be most effective when designed around this principle.

cs.HC

新论文 · v1arXiv:2611.19984

VoiceGuard: An Audio-Native LLM-VLA Pipeline for Wheelchair-Mounted Assistive Manipulation

Bang Xiao, Rodolfo Cossovich

原文摘要

Wheelchair-mounted robotic arms can help people with limited upper-limb mobility reach and manipulate everyday objects, but operating them typically requires stepwise joystick control and frequent mode switching. Natural-language interfaces could let users express task-level goals, yet they must handle ambiguous requests, distinguish commands from nearby conversation, and support interruption. We present VoiceGuard, a voice interface that separates spoken intent from robot execution through structured request validation and a local stop mechanism. On-device detectors handle the wake phrase and stop commands, an audio-native large language model (LLM) routes each request into a structured function packet, a rule-based ToolDispatcher accepts, rejects, or clarifies the packet, and a SmolVLA vision-language-action (VLA) policy executes accepted tasks on a low-cost SO-101 arm. Preliminary tests showed that the system correctly handled 55 of 60 voice commands, including ambiguous and non-directed utterances, completed 16 of 20 deliveries, and stopped the arm on all 20 stop commands with a median latency of 210 ms. We demonstrate the feasibility of combining flexible spoken input with constrained task execution and local interruption for wheelchair-mounted assistive manipulation.

cs.HC

新论文 · v1arXiv:2611.19932

From Companion to Guardian: Designing an Emergency Support System Using a Quadruped Robot for Older Adults

Chunyang Meng, Eduardo B. Sandoval, Josh Andres, Francisco Cruz, Mari Velonaki

原文摘要

As older adults increasingly live alone, emergency support becomes an important function for home companion robots. In Australia, demand for the care and support workforce is projected to nearly double between 2020-21 and 2049-50. Service robots such as robot dogs may support older adults by combining everyday companionship with assistance when human support is not immediately available. We present the design and implementation of a domestic companion-robot system on a Unitree Go1 quadruped platform that combines companionship with emergency awareness and response. The system uses a three-stage interaction model consisting of companion, danger-awareness, and emergency modes. A rule-based escalation policy combines signs detected from visual and speech input to determine the current risk level and adjust how long the robot waits for the user to confirm safety before entering emergency mode. Additional detected signs can shorten this waiting time. Users can confirm safety, request immediate help, stop robot motion, or reset the system. We verified the implemented decision rules and escalation timing through 105 automated trials and 25 staged physical trials. Additional visual evidence shortened the waiting time, and the system entered emergency mode when the waiting time ended without confirmation.

cs.RO · cs.HC

新论文 · v1arXiv:2611.19843

Sangyadhi: An Analytical Framework for Diagnosing and Investigating Collective Care

Shyama Sastha Krishnamoorthy Srinivasan, Mohan Kumar, Pushpendra Singh

原文摘要

While HCI has expanded from Personal to Family Informatics, researchers still lack a critical analytical vocabulary to diagnose what truly constitutes a collective care context. We introduce Sangyadhi, an analytical sociotechnical framework that synthesizes Situated Action, Distributed Cognition, the Capabilities Approach, and Actor-Network Theory to investigate multi-actor care ecologies. The framework articulates four interdependent analytical lenses: contextual grounding, distributed responsibility, trust-mediated sharing, and collaborative actionability. To demonstrate its diagnostic utility, we apply Sangyadhi to critically audit a decade of HCI digital health literature across self-tracking, family informatics, and clinical AI---surfacing structural omissions in how shifting authority, dynamic trust, and AI escalation are conceptualized. Ultimately, the goal of Sangyadhi is to equip researchers with an analytical blueprint for diagnosing observed care contexts, structuring field inquiries, and evaluating future technologies.

cs.HC

新论文 · v1arXiv:2611.19810

Developing JEEVHITAA: Designing and Evaluating a Human-Centered AI Ecosystem for Collective Care

Shyama Sastha Krishnamoorthy Srinivasan, Harsh Pala, Shahnawaz, Mohan Kumar, Pushpendra Singh

原文摘要

Health management is often a collective activity, involving family members and close relations in monitoring, interpreting, and coordinating care. Yet, most digital health technologies remain individual-centric, offering limited support for the distributed responsibilities and negotiated information sharing that characterize collective care. We present JEEVHITAA, a human-centered AI ecosystem designed to address this gap. Drawing on existing literature on collective health practices, we identify key requirements and translate them into a canonical ontology and a versioned data schema that underpin a mobile ecosystem integrating wearable data, role-aware sharing, granular access controls, auditable histories, and AI-assisted health summarization and verification. We first evaluated core system primitives using 1,000 ontology-driven synthetic care circles to test data visibility and information-processing workflows. We then conducted a controlled lab study with 13 subject--care-actor dyads (26 participants), combining task-based interactions, semi-structured interviews, the System Usability Scale, and component-level usability assessments. Findings indicate positive perceptions of usability and highlight the value of granular sharing and transparent information provenance. They also expose tensions between reciprocal transparency and surveillance, and between AI-mediated assistance and potentially intrusive notifications. We discuss implications for designing accountable, context-sensitive technologies that support collective care.

cs.HC · cs.ET