2026-08论文中文摘要

• 基于假设驱动搜索的移动应用数据库中可扩展个人身份信息（PII）发现

  Scalable PII Discovery in Mobile App Databases via Hypothesis-Driven Search

  arXiv 2608.21469 · 2026-08-25

• 用于橡胶混凝土缺陷表征的近程摄影测量生成三维点云

  3D Point Cloud from Close-Range Photogrammetry for Defect Characterisation of Rubberised Concrete

  arXiv 2608.21468 · 2026-08-25

• 有限马尔可夫链k-块平均核的谱划分

  Spectral partitioning for $k$-block averaging kernels of finite Markov chains

  arXiv 2608.21466 · 2026-08-25

• 关系子的稳定换位子长度并非单关系群不变量

  The stable commutator length of a relator is not a one-relator group invariant

  arXiv 2608.21465 · 2026-08-25

• 在空气质量预测中使用QHAdamW的增强型人工神经网络

  Enhanced Artificial Neural Networks Using QHAdamW in Air Quality Forecasting

  arXiv 2608.21463 · 2026-08-25

• CyrillicQA：语音编码的秘密语言对大语言模型性能的影响

  CyrillicQA: The Influence of Phonetically Encoded Secret Language on LLM Performance

  arXiv 2608.21462 · 2026-08-25

• Bent函数与完全Maiorana-McFarland类

  Bent Functions and the Completed Maiorana-McFarland Class

  arXiv 2608.21461 · 2026-08-25

• FigmaTrace：捕捉人类Figma设计工作流程中的创意细节

  FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows

  arXiv 2608.21460 · 2026-08-25

• 基于狄拉克夸克哈密顿量和数值方法的π介子与K介子质量的类氢模型

  A Hydrogen-Like Model for Pion and Kaon Masses Based on Dirac Quark-Hamiltonians and Numerical Methods

  arXiv 2608.21459 · 2026-08-25

• SAGA：局部到全局软件架构的比较定理——从语义修复上同调到代数几何下降

  SAGA: A Comparison Theorem for Local-to-Global Software Architecture - From Semantic Repair Cohomology to Algebraic-Geometric Descent

  arXiv 2608.21458 · 2026-08-25

• CLSC DETR：基于跨层几何支持的可靠候选排序用于无人机小目标检测

  CLSC DETR: Reliable Candidate Ranking via Cross Layer Geometric Support for UAV Small Object Detection

  arXiv 2608.21457 · 2026-08-25

• 关于凸序列的刻画、分解与稳定性

  On characterizations, Decompositions, and Stability of Convex Sequences

  arXiv 2608.21456 · 2026-08-25

• 涉及指数函数、误差函数与抛物柱函数的新型拉普拉斯卷积积分及其在传热和线性粘弹性中的应用

  New Laplace convolution integrals involving exponential, error, and parabolic cylinder functions with applications in heat transfer and linear viscoelasticity

  arXiv 2608.21453 · 2026-08-25

• 载氢金属中质子的相干振荡

  Coherent Oscillations of Protons in Hydrogen-loaded Metals

  arXiv 2608.21452 · 2026-08-25

• 量子统计力学概率的幂级数及其在氦气第二维里系数中的结果

  Power Series for the Quantum Statistical Mechanics Probability with Results for the Second Virial Coefficient of Helium

  arXiv 2608.21451 · 2026-08-25

• 超越视觉相似度：面向基于知识的视觉问答的实体对齐检索

  Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering

  arXiv 2608.21450 · 2026-08-25

• 时间序列分类中可解释人工智能的软件框架：系统综述

  Software Frameworks for Explainable AI in Time Series Classification: A Systematic Review

  arXiv 2608.21449 · 2026-08-25

• 黑色素瘤中的DNA甲基化谱分析：从病变分类到治疗分层

  DNA Methylation Profiling in Melanoma: From Lesion Classification to Therapeutic Stratification

  arXiv 2608.21448 · 2026-08-25

• BIMScript：用于BIM导入的材料感知结构化场景程序

  BIMScript: Material-Aware Structured Scene Programs for BIM Ingestion

  arXiv 2608.21447 · 2026-08-25

• HiFiC-G：适配HiFiC用于Hi-C接触矩阵

  HiFiC-G: Adapting HiFiC for Hi-C Contact Matrices

  arXiv 2608.21446 · 2026-08-25

• ViTexSZ：用于脑电图癫痫发作检测的异构视觉-文本知识蒸馏框架

  ViTexSZ: Heterogeneous Vision-Text Knowledge Distillation for EEG Seizure Detection

  arXiv 2608.21445 · 2026-08-25

• 面向安全关键多无人机系统的智能体人工智能：挑战与机遇

  Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities

  arXiv 2608.21444 · 2026-08-25

• 基于跨模态注意力先验的文本引导视觉依赖图学习

  Text-Guided Visual Dependency Graph Learning with Cross-Modal Attention Priors

  arXiv 2608.21443 · 2026-08-25

• 构建基于AI的撕囊术技能迁移的预测手术路径

  Constructing Predictive Surgical Path for AI-based Capsulorhexis Skill Transfer

  arXiv 2608.21441 · 2026-08-25

• Geo-VLA：通过内化地图语义实现几何感知的视觉-语言-动作规划

  Geo-VLA: Geometry-Aware Vision-Language-Action Planning via Internalization of Map Semantics

  arXiv 2608.21440 · 2026-08-25

• WorldMind：用于状态感知NPC行为的解耦游戏世界模型

  WorldMind: Decoupled Game World Model for State-Aware NPC Behavior

  arXiv 2608.21439 · 2026-08-25

• DesignAgent3D：通过类设计师多模态推理实现交互式3D场景编辑

  DesignAgent3D: Interactive 3D Scene Editing via Designer-like Multimodal Reasoning

  arXiv 2608.21438 · 2026-08-25

• 量子技术：系统级性能与验证优先级

  Quantum Technologies: System-Level Performance and Validation Priorities

  arXiv 2608.21436 · 2026-08-25

• 非厄米散射中倏逝隧穿与传输延迟的复时间参数化

  Complex-Time Parametrization of Evanescent Tunneling and Transmission Delay in non-Hermitian Scattering

  arXiv 2608.21435 · 2026-08-25

• 来自秩一淬火的最大秩压缩：高斯玻色系统的精确谱可达性定理

  Maximal-Rank Squeezing from Rank-One Quenches: An Exact Spectral-Reachability Theorem for Gaussian Bosonic Systems

  arXiv 2608.21434 · 2026-08-25

• 利用双致密天体并合产生的引力波信号检验f(R)引力

  Testing f(R) gravity using gravitational-wave signals from binary mergers

  arXiv 2608.21432 · 2026-08-25

• 基于结构化上下文推理提升基于知识的视觉问答性能

  Boosting Knowledge-based Visual Question Answering with Structured Context Reasoning

  arXiv 2608.21431 · 2026-08-25

• 评估热门好莱坞电影的多模态叙事理解能力

  Evaluating Multimodal Narrative Understanding of Popular Hollywood Films

  arXiv 2608.21430 · 2026-08-25

• 动画电影中的性别代表性衡量

  Measuring Gender Representation in Animated Films

  arXiv 2608.21429 · 2026-08-25

• 量子Petri网中的可达性问题

  On the Reachability Problem in Quantum Petri Nets

  arXiv 2608.21428 · 2026-08-25

• 基于DenseNet的少样本跨数据集结核检测

  Few-Shot Cross-Dataset Adaptation for Tuberculosis Detection Using DenseNet

  arXiv 2608.21427 · 2026-08-25

• 服装生产的AI视觉检测

  AI Visual Inspection for Garment Production

  arXiv 2608.21426 · 2026-08-25

• 对齐人类感知：用于视频生成的校准分布奖励学习

  Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation

  arXiv 2608.21425 · 2026-08-25

• EditStream：用于交互式视频生成与编辑的统一自回归框架

  EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing

  arXiv 2608.21424 · 2026-08-25

• 智能体安全：LLM驱动渗透测试的工具、失效模式与设计法则体系化研究

  Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing

  arXiv 2608.21423 · 2026-08-25

• 微笑的拓扑：牙科成像中的持续同调

  Topology of a Smile: Persistent Homology in Dental Imaging

  arXiv 2608.21422 · 2026-08-25

• 有向级联生成新的临界普适类

  Directed Cascades Generate New Critical Universality Classes

  arXiv 2608.21421 · 2026-08-25

• 在面向弱势人群的人机交互（HRI）中评估人类与大语言模型（LLM）生成的主题分析：一项比较与伦理分析

  Evaluating Human and LLM-Generated Thematic Analysis in HRI for Vulnerable Populations: A Comparative and Ethical Analysis

  arXiv 2608.21420 · 2026-08-25

• 能量-动量平方引力中的中子星：结构、稳定性与多信使约束

  Neutron Stars in Energy--Momentum Squared Gravity: Structure, Stability, and Multimessenger Constraints

  arXiv 2608.21419 · 2026-08-25

• 面向制造知识图谱的可组合信任基础设施：跨系统溯源、时序推理与决策可追溯性

  Composable Trust Infrastructure for Manufacturing Knowledge Graphs: Cross-System Provenance, Temporal Reasoning, and Decision Traceability

  arXiv 2608.21418 · 2026-08-25

• 基于检索的机器人程序生成与基于仿真的修正：通过模型上下文协议

  Retrieval-grounded robot program generation and simulation-based correction via Model Context Protocol

  arXiv 2608.21417 · 2026-08-25

• 可操作的数字孪生诊所支持具身人工智能的任务型评估

  Operational digital twin clinics enable task-based evaluation of embodied AI

  arXiv 2608.21416 · 2026-08-25

• 基于反事实集成解码缓解大视觉语言模型中的偏差

  Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

  arXiv 2608.21415 · 2026-08-25

• RiskWorld：面向自动驾驶风险识别的以对象为中心的潜在世界建模

  RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification

  arXiv 2608.21414 · 2026-08-25

• 基于生活模式模拟的合成废水流行病学数据生成

  Synthetic Wastewater Epidemiology Data Generation using Patterns-of-Life Simulation

  arXiv 2608.21413 · 2026-08-25