2026-10论文中文摘要
缓解基于GenAI的自适应系统中的不确定性交互：愿景、挑战与初步指南
Mitigating Uncertainty Interactions in GenAI-based Adaptive Systems: Vision, Challenges and Preliminary Guidelines
arXiv 2610.08881 · 2026-10-08基于物理的球体填充用于拉格朗日网格变形
Physics-based Sphere Packing for Lagrangian Mesh Morphing
arXiv 2610.08880 · 2026-10-08微型中文BERT预训练：MLM、WWM与MacBERT策略的受控比较
Tiny-Scale Chinese BERT Pretraining: A Controlled Comparison of MLM, WWM, and MacBERT Strategies
arXiv 2610.08879 · 2026-10-08人工智能如何可能消灭人类？文明风险的失效模式分析
How Could AI Eliminate Humanity? A Failure-Mode Analysis of Civilizational Risk
arXiv 2610.08878 · 2026-10-08损耗主导离子束输运的可微代理模型
A Differentiable Surrogate for Loss-Dominated Ion Beam Transport
arXiv 2610.08877 · 2026-10-08面向多参数位翻转扰动的神经网络验证
Towards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations
arXiv 2610.08876 · 2026-10-08金属纳米线气凝胶中的热扩散率
Thermal Diffusivity in Metallic Nanowire Aerogels
arXiv 2610.08874 · 2026-10-08Banach 序列空间中单项式收敛域
Domains of Monomial Convergence in Banach Sequence Spaces
arXiv 2610.08873 · 2026-10-08在Kesten-Stigum阈值处慢胜于快：稀疏随机块模型中信息-计算间隙的极小极大、Fisher信息与置信传播刻画
Slow Beats Fast at the Kesten-Stigum Threshold: Minimax, Fisher-Information and Belief-Propagation Characterizations of the Information-Computation Gap in Sparse Stochastic Block Models
arXiv 2610.08872 · 2026-10-08CredLeakBench：评估LLM代理中的凭证泄露与恢复
CredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents
arXiv 2610.08871 · 2026-10-08从可穿戴接口到灵巧策略：接触转移与触觉表征
From Wearable Interfaces to Dexterous Policies: Contact Shifts and Tactile Representations
arXiv 2610.08870 · 2026-10-08受监管信用评分中的学习单调循环特征：框架的代价与宏观条件化的必要性
Learned Monotone Recurrent Features in Governed Credit Scoring: The Price of the Frame and the Necessity of Macro Conditioning
arXiv 2610.08869 · 2026-10-08可见光谱光学隐蔽信道在商用智能照明中的应用
Visible-Spectrum Optical Covert Channels in Commodity Smart Lighting
arXiv 2610.08868 · 2026-10-08基于机器学习的物联网入侵检测在边缘、雾和云架构中的部署感知可行性框架
A Deployment-Aware Feasibility Framework for Machine Learning-Based IoT Intrusion Detection Across Edge, Fog, and Cloud Architectures
arXiv 2610.08867 · 2026-10-08几何感知扩散近似后验采样用于稀疏视图和有限角度CT
Geometry-Aware Diffusion Approximate Posterior Sampling for Sparse-View and Limited-Angle CT
arXiv 2610.08866 · 2026-10-08短长度网格模式在可分离排列上的分布
Distributions of Mesh Patterns of Short Lengths on Separable Permutations
arXiv 2610.08865 · 2026-10-08对抗强化学习用于端口扫描规避：边缘部署IDS中的攻击者特征可见性
Adversarial RL for Port-Scan Evasion: Attacker Feature Visibility in Edge-Deployed IDS
arXiv 2610.08864 · 2026-10-08无轨迹数据的轨迹规划：一种流形引导方法
Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
arXiv 2610.08863 · 2026-10-08CIRRA：面向交互式家庭任务中具身机器人智能体的双层级持续指令协调与持续执行
CIRRA: Dual-Level Continual Instruction Reconciliation with Ongoing Execution for Embodied Robot Agents in Interactive Household Tasks
arXiv 2610.08862 · 2026-10-08利用信息论方法重建未破译信息的几何与结构方面
Reconstruction of Geometric and Structural Aspects of Undeciphered Messages by Information-theoretic Methods
arXiv 2610.08861 · 2026-10-08引力散射振幅的共线和高能极限
Gravitational scattering amplitudes in collinear and high-energy limits
arXiv 2610.08860 · 2026-10-08代数广义Ricci孤立子的调和挠率与可解扩张的结构
Harmonic torsion of algebraic generalized Ricci solitons and the structure of solvable extensions
arXiv 2610.08859 · 2026-10-08LRCC：基于条件计算泛化低秩压缩
LRCC: Generalizing Low-Rank Compression with Conditional Computation
arXiv 2610.08858 · 2026-10-08映射类群与自由群自同构群中的无穷多个 Nielsen 类
Infinitely many Nielsen classes in mapping class groups and free-group automorphism groups
arXiv 2610.08857 · 2026-10-08基孔肯雅热当前控制策略的动力学洞察
Dynamical Insights into the Current Control Strategies for Chikungunya
arXiv 2610.08856 · 2026-10-08非最小爱因斯坦-杨-米尔斯黑洞周围中性及带电标量云的寿命反转
Lifetime reversals of neutral and charged scalar clouds around nonminimal Einstein-Yang-Mills black holes
arXiv 2610.08855 · 2026-10-08认证切分：最大吞噬分词的可判定性与锚点供给
Certified Splitting: Decidability and Anchor Supply for Maximal-Munch Tokenization
arXiv 2610.08854 · 2026-10-08宇宙热引力的相空间结构
Phase-space structure of cosmological thermogravity
arXiv 2610.08853 · 2026-10-08基于模型的强化学习实现自主液滴导航：零样本迁移与涌现动力学
Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics
arXiv 2610.08852 · 2026-10-08QuanLing：西罗曼语语言距离量化的跨分支验证
QuanLing: Cross-Branch Validation of Language Distance Quantification on Western Romance
arXiv 2610.08851 · 2026-10-08未被听到但可识别：用于乐器识别的超声波特征
Unheard but Recognizable: Ultrasonic Signatures for Musical Instrument Recognition
arXiv 2610.08850 · 2026-10-08基于语义标签的腹部超声模拟：配对标签到物理图像翻译
Abdominal Ultrasound Simulation from Semantic Labels using Paired Label-to-Physics-Based Image Translation
arXiv 2610.08849 · 2026-10-08STRIDE：纵向胶质母细胞瘤MRI中区间条件疾病演变的时空表示
STRIDE: Spatial-Temporal Representation for Interval-conditioned Disease Evolution in Longitudinal Glioblastoma MRI
arXiv 2610.08848 · 2026-10-08使用Whisper的印地语带时间戳语音转录
Timestamped Hindi speech transcription using Whisper
arXiv 2610.08847 · 2026-10-08Indic-CLAP：通过跨语言蒸馏实现印度语言的文本-音频理解
Indic-CLAP: Text--Audio Understanding in Indic Languages via Cross-Lingual Distillation
arXiv 2610.08846 · 2026-10-08统一共享编码器在混合小波提示调优的防欺骗说话人验证中的应用
Unified Shared Encoder in Spoof-Aware Speaker Verification with Hybrid Wavelet Prompt Tuning
arXiv 2610.08845 · 2026-10-08UZH-CL 在 ArA-DF 2026：面向阿拉伯语音深度伪造检测的提示微调基础模型与轨道自适应分数融合
UZH-CL at ArA-DF 2026: Prompt-Tuned Foundation Models and Track-Adaptive Score Fusion for Arabic Speech Deepfake Detection
arXiv 2610.08844 · 2026-10-08质子治疗中剂量分布去噪深度学习模型的优化
Optimization of Deep Learning Model for Denoising Dose Profiles in Proton Therapy
arXiv 2610.08843 · 2026-10-08超越风险预测：面向可解释自杀风险评估的证据锚定与心理社会因素验证
Beyond Risk Prediction: Evidence Grounding and Psychosocial Factor Verification for Explainable Suicide Risk Assessment
arXiv 2610.08842 · 2026-10-08相干量子正弦积分黑洞中的阴影特征与近地平线能量积累
Shadow signatures and near-horizon energy accumulation in coherent quantum sine-integral black holes
arXiv 2610.08841 · 2026-10-08超越谄媚评分：任务、模型与压力如何塑造大语言模型的让步行为
Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding
arXiv 2610.08840 · 2026-10-08真实语音与合成语音在不同熟悉度水平下的语调感知：一项等价性评估的初步研究
Intonation Perception in Real and Synthetic Speech across Varying Familiarity Levels: A Pilot Study of Equivalence Assessment
arXiv 2610.08839 · 2026-10-08深度学习在纵向医学影像中的应用：范围综述
Deep Learning for Longitudinal Medical Imaging: A Scoping Review
arXiv 2610.08838 · 2026-10-08来自Yang-Baxter算子的曲面辫子不变量及其上同调
Surface Braid Invariants from Yang-Baxter Operators and Their Cohomology
arXiv 2610.08837 · 2026-10-08用DESI DR2重子声学振荡观测和机器学习方法重新审视哈勃常数危机
Revisiting the Hubble Tension with DESI DR2 Baryon Acoustic Oscillation Observations and Machine Learning Methods
arXiv 2610.08836 · 2026-10-08JoyAI-Voice 2.0：具有语义-声学联合表示的全连续自回归语音生成模型
JoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint Representation
arXiv 2610.08834 · 2026-10-08CoDR：扩散语言模型的无训练置信度漂移重掩码
CoDR: Training-Free Confidence-Drift Remasking for Diffusion Language Models
arXiv 2610.08833 · 2026-10-08引力、熵与第二定律：一个教学视角
Gravity, Entropy, and the Second Law: A Pedagogical Perspective
arXiv 2610.08832 · 2026-10-08词错误率够用吗？重新思考语音隐私评估中的实体感知指标
Is Word Error Rate Enough? Rethinking Privacy Evaluation in Speech with Entity-Aware Metrics
arXiv 2610.08831 · 2026-10-08MoR-MLLM：高效多模态大语言模型的递归混合
MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models
arXiv 2610.08830 · 2026-10-08
