2026-08论文中文摘要
CheckOne：用于视觉Transformer的轻量级故障检测与缓解方法
CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers
arXiv 2608.04035 · 2026-08-06基于原子越狱策略解耦与组合的多模态自动红队评估
A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination
arXiv 2608.04034 · 2026-08-06SoK：前沿人工智能如何重塑关键基础设施中的系统级安全风险动态
SoK: How Frontier AI Reshapes System-Level Security Risk Dynamics in Critical Infrastructure
arXiv 2608.04033 · 2026-08-06EDATracer：用于大规模EDA工件分析的智能体框架
EDATracer: An Agentic Framework for Large-Scale EDA Artifact Analysis
arXiv 2608.04032 · 2026-08-06硬件实现的模糊推理：架构、平台与新兴趋势
Hardware-Enabled Fuzzy Inference: Architectures, Platforms, and Emerging Trends
arXiv 2608.04031 · 2026-08-06NuclearDiffusion：用于学习核能概念的文生成像基础模型
NuclearDiffusion: Text-to-Image Foundation Models for Learning Nuclear Energy Concepts
arXiv 2608.04030 · 2026-08-06防御基于毫米波的对比学习人体活动识别系统免受对抗性标签翻转攻击
Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping
arXiv 2608.04029 · 2026-08-06受林德布拉德启发的带可分离旋转与耗散的多时间尺度储备池计算
Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation
arXiv 2608.04028 · 2026-08-06用全卷积神经网络学习分辨中子共振
Learning to Resolve Neutron Resonances with Fully Convolutional Neural Networks
arXiv 2608.04027 · 2026-08-06面向病理生存模型的感知删失共形下界预测边界的多队列验证
A Multi-Cohort Validation of Censoring-Aware Conformal Lower Predictive Bounds for Pathology Survival Models
arXiv 2608.04025 · 2026-08-06乘客头部位置不确定性对感染风险预测的影响
Influence of passenger head-position uncertainty on infection risk predictions
arXiv 2608.04024 · 2026-08-06基于可组合函数系统的量子设备通用图形渲染
General purpose graphical rendering on quantum devices with composable function systems
arXiv 2608.04022 · 2026-08-06当多变为少：语言模型中与位置相关的重复效应
When More Becomes Less: Position-Dependent Repetition Effects in Language Models
arXiv 2608.04021 · 2026-08-06人工制度：制度设计如何塑造大语言模型（LLM）模拟
Artificial Institutions: How Institutional Design Shapes LLM Simulations
arXiv 2608.04020 · 2026-08-06硅谷的隐秘软肋：数据工作价值链中的算法剥削与健康问题
Hidden Underbelly of the Silicon Valley: Algorithmic Exploitation and Health in Data Work Value Chains
arXiv 2608.04019 · 2026-08-06管控智能体AI系统的执行风险：一种基于轨迹的红队测试框架
Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Teaming
arXiv 2608.04018 · 2026-08-06高等远程教育中通信的定性比较研究
A Qualitative Comparative Study of Communication in Higher Distance Education
arXiv 2608.04017 · 2026-08-06人工智能驱动的多模态表征学习用于发现社会经济劣势、心理社会因素与心脏代谢共病的潜在中介结构：来自All of Us研究计划的见解
AI-driven Multimodal Representation Learning for Latent Mediation Structure Discovery of Socioeconomic Disadvantage, Psychosocial Factors, and Cardiometabolic Multimorbidity: Insights from the All of Us Research Program
arXiv 2608.04016 · 2026-08-06通过大语言模型提示学习实现古典拉丁语命名实体识别的迁移学习
Transfer Learning for Named Entity Recognition of Classical Latin through LLM Prompting
arXiv 2608.04015 · 2026-08-06次主导（极小极大）超度量的汉明-利普希茨型稳定性：理论与简单证明
On Hamming-Lipschitz Type Stability of the Subdominant (Minmax) Ultrametric: Theory and Simple Proofs
arXiv 2608.04014 · 2026-08-06C²MOE：面向不完整多模态情感学习的一致性与互补性引导的混合专家模型
C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning
arXiv 2608.04013 · 2026-08-06基于冗余调整人工年龄评分（AAS）的AI系统长期持久性理论
A Long-Run Persistence Theory for AI Systems under the Redundancy-Adjusted Artificial Age Score (AAS)
arXiv 2608.04012 · 2026-08-06迈向人工智能法律智能的新推理语法：以《梅塞莱法典》作为其语义协议
Towards a New Grammar of Reasoning for Artificial Legal Intelligence and the Mecelle as Its Semantic Protocol
arXiv 2608.04011 · 2026-08-06感知锚定：用于无训练开放词汇语义分割的原型引导文本校准
Perceptual Anchoring: Prototype-Guided Text Calibration for Training-free Open-Vocabulary Semantic Segmentation
arXiv 2608.03991 · 2026-08-06实值化张量网络：在实值矩阵加速器上的量子电路模拟
Realified tensor networks: quantum circuit simulation on real-valued matrix accelerators
arXiv 2608.03987 · 2026-08-06局部有界积分曲率曲面的分析
Analysis on surfaces with locally bounded integral curvature
arXiv 2608.03982 · 2026-08-06锌-64的统计与非统计γ衰变性质
Statistical and non-statistical $γ$-decay properties of $^{64}$Zn
arXiv 2608.03943 · 2026-08-06交叉集中采样下的鲁棒低张量秩补全
Robust Low-Tubal-Rank Tensor Completion under Cross-Concentrated Sampling
arXiv 2608.03928 · 2026-08-06基于有理指数的新复值调和态射
New Complex-Valued Harmonic Morphisms via Rational Exponents
arXiv 2608.03905 · 2026-08-06基于切片沃尔什斯坦核的拓扑聚类
Topological Clustering via Sliced Wasserstien Kernels
arXiv 2608.03891 · 2026-08-06全抛物型Keller--Segel系统有界性的显式逻辑斯蒂阻尼准则
An Explicit Logistic Damping Criterion for Boundedness in a Fully Parabolic Keller--Segel System
arXiv 2608.03869 · 2026-08-06来自内部构型空间的广义空间群
Generalized Space Groups from Internal Configuration Spaces
arXiv 2608.03808 · 2026-08-06当输出分散时，认知修正会随之而来吗？面向机器集体的黑盒耦合诊断方法
When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Diagnostic for Machine Collectives
arXiv 2608.03722 · 2026-08-06二维近藤晶格中量子相变的腔调控
Cavity control of quantum phase transitions in a two-dimensional Kondo lattice
arXiv 2608.03714 · 2026-08-06通过滞后补偿、迭代学习与视觉传感实现电子显微镜中的精密样品定位
Precision Specimen Positioning in Electron Microscopy through Hysteresis Compensation, Iterative Learning, and Vision-Based Sensing
arXiv 2608.03669 · 2026-08-06Hi-TTRL：利用提示调控测试时强化学习的共识
Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning
arXiv 2608.03545 · 2026-08-06非结构化生物医学文本标注的一致性度量
Consensus Measures for Unstructured Biomedical Text Annotations
arXiv 2608.03529 · 2026-08-06ConlangBench：通过多样人造语言探索大语言模型的语言知识与学习
ConlangBench: Exploring Language Knowledge and Learning in LLMs through Diverse Constructed Languages
arXiv 2608.03505 · 2026-08-06用于发现和复用高阶网络数据集的仓库
A repository for discovery and reuse of higher-order network datasets
arXiv 2608.03491 · 2026-08-06RAG-Stack：协同优化RAG服务性能与质量
RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
arXiv 2608.03487 · 2026-08-06当正确解重复时：面向GRPO的稀有感知信用再分配
When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO
arXiv 2608.03467 · 2026-08-06RoboReact：基于生成的自我中心视频的智能体技能蒸馏，实现通用全身操控
RoboReact: Agentic Skill Distillation from Generated Egocentric Videos for Generalizable Whole-Body Manipulation
arXiv 2608.03387 · 2026-08-06CROSS：用于遥感指称分割的级联蒸馏与双约束 grounding
CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation
arXiv 2608.03147 · 2026-08-06Maglev：滑动循环记忆
Maglev: Sliding Recurrent Memory
arXiv 2608.02870 · 2026-08-06用于 Lenticular 胶片色彩重建的人机交互深度学习框架
A Human-in-the-Loop Deep Learning Framework for Color Reconstruction of Lenticular Films
arXiv 2608.02835 · 2026-08-06Bi₂Te₃上Fe吸附原子的位点对称性破缺
Broken site symmetry of Fe adatoms on Bi$_2$Te$_3$
arXiv 2608.02770 · 2026-08-06对齐机制中的盲区：量化大语言模型的生物安全风险
A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models
arXiv 2608.02684 · 2026-08-06带拓扑荷的Morris-Thorne型虫洞与能量条件
Topologically Charged Morris-Thorne-type Wormholes and the Energy Conditions
arXiv 2608.02652 · 2026-08-06变半径圆盘变换与扎尔克曼的面积积分问题
Variable-Radius Disk Transforms and an Area-Integral Problem of Zalcman
arXiv 2608.02546 · 2026-08-06图表类型边界的定义
On Defining Chart Types Boundaries
arXiv 2608.02512 · 2026-08-06
