2026-08论文中文摘要
用于成员推断与AI生成文本检测的令牌级似然数组回归
Token-Level Likelihood-Array Regression for Membership Inference and AI-Generated Text Detection
arXiv 2608.22179 · 2026-08-25稀薄非相对论中子气体中的等离激元极化激元
Plasmon-polaritons in a rarefied nonrelativistic neutron gas
arXiv 2608.22177 · 2026-08-25采用开源权重大语言模型的角色专业化智能体混合架构用于临床预测
Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction
arXiv 2608.22176 · 2026-08-25稀有事件的非交换定律
Non-commutative law of rare events
arXiv 2608.22175 · 2026-08-25球面上的各向同性正定函数：偶维Gneiting问题
Isotropic Positive Definite Functions on Spheres: Even-Dimensional Gneiting's Problem
arXiv 2608.22173 · 2026-08-25未来多目标光谱仪的技术规格建模
Modeling the technical specifications for future multi-object spectroscopy instrumentation
arXiv 2608.22172 · 2026-08-25重新审视功能多组典型相关分析：从有限维样本到无限维总体
Functional Multiple-Set Canonical Correlation Analysis Revisited: From Finite-Dimensional Samples to Infinite-Dimensional Populations
arXiv 2608.22170 · 2026-08-25基于多智能体强化学习的可重构智能表面序列拍卖：物理层安全分析
MARL-Based Sequential RIS Auctions: A Physical-Layer Security Analysis
arXiv 2608.22169 · 2026-08-25纠缠Dicke态的确定性制备
Deterministic preparation of entangled Dicke states
arXiv 2608.22168 · 2026-08-25MCP-Universe RL：一种通过强化学习训练MCP工具使用智能体的框架
MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning
arXiv 2608.22167 · 2026-08-25由李双代数和置换双代数通过张量积构造的莱布尼茨双代数
Leibniz bialgebras constructed by tensor product from Lie bialgebras and perm bialgebras
arXiv 2608.22166 · 2026-08-25基于加权顺序统计量的加性噪声鲁棒尺度估计
Robust Scale Estimation in Additive Noise via Weighted Order Statistics
arXiv 2608.22165 · 2026-08-25脉冲星计时阵列引力波背景中的各向异性：它们能告诉我们关于超大质量黑洞双星的什么信息
Anisotropies in the PTA gravitational wave background: what can they teach us about supermassive black hole binaries?
arXiv 2608.22164 · 2026-08-25美国北达科他州布罗姆溪地层的盆地尺度多存储项目建模：统一模型与不确定性量化
Basin-Scale Modeling of Multiple Storage Projects in the Broom Creek Formation, North Dakota, USA: Unified Model and Uncertainty Quantification
arXiv 2608.22163 · 2026-08-25抛物型方程两步显式指数Adams方法的后验误差估计
A posteriori error estimates for the two-step explicit exponential Adams method for parabolic equations
arXiv 2608.22162 · 2026-08-25面向作者身份重识别的聚合感知合成文本生成
Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification
arXiv 2608.22161 · 2026-08-25纠缠支配投影系综中随机性的早期增长
Entanglement governs early-time growth of randomness in projected ensembles
arXiv 2608.22158 · 2026-08-25有限状态马尔可夫GL(2)上同调在零李雅普诺夫间隙处的对数-赫尔德连续性
Log-Höder continuity at zero Lyapunov gap for finite state Markov $GL(2)$-cocycles
arXiv 2608.22157 · 2026-08-25SIM辅助无小区大规模MIMO中混合数字-波波束成形的高效交替优化
Efficient Alternating Optimization for Hybrid Digital-Wave Beamforming in SIM-Assisted Cell-Free Massive MIMO
arXiv 2608.22156 · 2026-08-25为何鲁棒性会减少叠加？
Why Does Robustness Reduce Superposition?
arXiv 2608.22155 · 2026-08-25结合贝叶斯-联结主义的混合模型实现更准确的行为预测
More accurate behavioral predictions with hybrid Bayesian-connectionist models
arXiv 2608.22154 · 2026-08-25从太空量化AI数据中心的氮氧化物（NO$_x$）排放量
Quantifying AI data center nitrogen oxide (NO$_x$) emissions from space
arXiv 2608.22153 · 2026-08-25面向可操作的可视化：十年之后，生成式AI带来了什么改变，又有什么是它做不到的
Towards Actionable Visualization: Ten Years Later, What Generative AI Changes and What It Cannot
arXiv 2608.22151 · 2026-08-25因果信念中的性别归因
Gender Attribution in Causal Beliefs
arXiv 2608.22150 · 2026-08-25矩阵谱的相干序列
Coherent sequences of matrix spectra
arXiv 2608.22148 · 2026-08-25单词子序列计数的对数凹性
Log-concavity of subsequence counts of words
arXiv 2608.22147 · 2026-08-25帖子标题中的因果语言塑造了在线对话的更深层拓扑结构
Causal Language in Post Titles Shapes Deeper Topological Structures of Online Conversations
arXiv 2608.22146 · 2026-08-25导致Adam停滞的损失景观特征：定义、估计器与预条件海森视角
Loss Landscape Features That Make Adam Stall: Definitions, Estimators, and the Preconditioned Hessian View
arXiv 2608.22145 · 2026-08-25当点变为圆：任意闭合六圆链的七圆定理
When Points Become Circles: The Seven Circles Theorem for Arbitrary Closed Six-Circle Chains
arXiv 2608.22144 · 2026-08-25小型视觉-语言模型在定性力学问题上的评估
Evaluation of Small Vision-Language Models on Qualitative Mechanical Problems
arXiv 2608.22143 · 2026-08-25通过隐变量增强型神经常微分方程学习含奇异性的降阶动力学
Learning Reduced-Order Dynamics with Singularity via Latent-Augmented Neural Ordinary Differential Equations
arXiv 2608.22142 · 2026-08-25MEMONDEMAND：面向大规模企业数据的内存管理系统
MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data
arXiv 2608.22141 · 2026-08-25词汇扰动破坏大语言模型推理：注意力转移的实证研究
Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion
arXiv 2608.22140 · 2026-08-25结构化扰动下语言模型的稳定性与失效行为测量
Measuring Stability and Failure Behavior in Language Models Under Structured Perturbations
arXiv 2608.22138 · 2026-08-25MegaMem：面向超大规模上下文窗口的检索解决方案
MegaMem: A Retrieval Solution for Ultra-Large Context Windows
arXiv 2608.22137 · 2026-08-25广义Su-Schrieffer-Heeger模型中拓扑边缘态产生的偶次谐波
Even-harmonic generation from topological edge states in generalized Su-Schrieffer-Heeger models
arXiv 2608.22136 · 2026-08-25GrOIL：基于图的领域本体归纳与受限大语言模型调解
GrOIL: Graph-Grounded Domain Ontology Induction with Constrained LLM Mediation
arXiv 2608.22135 · 2026-08-25A_N型局部卡拉比-丘轨形的Gopakumar-Vafa不变量
Gopakumar-Vafa Invariants for Local Calabi-Yau Orbifolds of $A_{N}$-type
arXiv 2608.22134 · 2026-08-25SSE-Bio：面向多跳生物医学推理的、具备智能体式检索策略的结构化自进化智能体
SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning
arXiv 2608.22132 · 2026-08-25TRACE：从不完美表面扫描中构建抗伪影的统计形状模型——以颅缝早闭三维摄影为例
TRACE: Artifact-Robust Statistical Shape Modeling from Imperfect Surface Scans - A Case Study in Craniosynostosis 3D Photography
arXiv 2608.22131 · 2026-08-25基于几何与知识基础的大语言模型推理的任务驱动型3D可打印性辅助
Task-Driven 3D Printability Assistance via Geometry- and Knowledge-Grounded LLM Reasoning
arXiv 2608.22128 · 2026-08-25区间序的物种
The species of interval orders
arXiv 2608.22125 · 2026-08-25大语言模型辅助写作值得实证评估
LLM assisted writing deserves empirical evaluation
arXiv 2608.22124 · 2026-08-25面向IEC 61869-9采样值通信的轻量级后量子安全框架
A Lightweight and Post-Quantum Secure Framework for IEC 61869-9 Sampled Value Communication
arXiv 2608.22123 · 2026-08-25从基于个体的随机流行病模型到异质性SIR方程
From Individual-Based Stochastic Epidemics to Heterogeneous SIR Equations
arXiv 2608.22122 · 2026-08-25来自单离子通道电流的球形膜的电压动力学
Voltage dynamics of spherical membranes from single ion channel currents
arXiv 2608.22121 · 2026-08-25去中心化在Top-K臂识别中的代价
The Price of Decentralization in Top-$K$ Arm Identification
arXiv 2608.22120 · 2026-08-25十阶素乘数：范数谱、局部图与选择性提升
Prime multipliers of order ten: norm spectra, local charts, and selective lifting
arXiv 2608.22119 · 2026-08-25RAG 坍缩：当检索到的文档为自主生成时，大语言模型（LLM）的响应会发生坍缩
RAG Collapse: LLM Responses Collapse When Retrieved Documents Are Self-Authored
arXiv 2608.22118 · 2026-08-25基于Sentinel-2影像的欧洲主要公路网车辆速度数据集（2022-2026）
Vehicle speed dataset for the major European road network derived from Sentinel-2 imagery, 2022-2026
arXiv 2608.22116 · 2026-08-25
