2026-08论文中文摘要
用于低场MRI的基于共基极BJT的低输入阻抗LNA概念
A Concept of LNA with Low Input Impedance Using Common Base BJT for Low-Field MRI
arXiv 2608.10225 · 2026-08-12领英的自进化智能体客户支持系统
Self-evolving Agentic Customer Support System at LinkedIn
arXiv 2608.10224 · 2026-08-12t=1时m-对称Macdonald正性的一个证明
A proof of the $m$-Symmetric Macdonald positivity at $t=1$
arXiv 2608.10223 · 2026-08-12一种基于JEPA的场层世界模型，用于衔接信道预测与估计
A JEPA-Based Field-Layer World Model for Bridging Channel Prediction and Estimation
arXiv 2608.10222 · 2026-08-12人形机器人在受限空间中通过自碰撞规避实现全身规划的参考方案
Whole-Body Planning for Humanoids Navigating Confined Spaces via Self-Collision Avoidance References
arXiv 2608.10220 · 2026-08-12伴随丛与弱博韦尔-博戈莫洛夫分解的一个判别准则
A criterion for associated bundles and the weak Beauville--Bogomolov decomposition
arXiv 2608.10219 · 2026-08-12思维病毒：多智能体大语言模型系统中的自传播思想
Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems
arXiv 2608.10218 · 2026-08-12用于完全不可压缩超弹性固体流固耦合的有限元浸入边界法的体积稳定混合格式
A Volumetrically Stabilized Mixed Formulation of the Finite Element Immersed Boundary Method for Fluid Structure Interaction with Fully Incompressible Hyperelastic Solids
arXiv 2608.10217 · 2026-08-12相似度门控认可反转：智能体系统中嵌入余弦阈值的有效性审计
Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems
arXiv 2608.10216 · 2026-08-12可解码但不可分离：训练数据粒度决定大语言模型的参数模块化
Decodable But Not Detachable: Training Data Granularity Determines Parametric Modularity in Large Language Models
arXiv 2608.10214 · 2026-08-12VeriFin：用于验证大语言模型生成的财务声明的神经符号框架
VeriFin: A Neurosymbolic Framework for Verifying LLM-Generated Financial Claims
arXiv 2608.10213 · 2026-08-12GMagAO-X的最终设计：GMT初光阶段的高对比度成像仪
The final design of GMagAO-X: high-contrast imaging at first-light of the GMT
arXiv 2608.10212 · 2026-08-12吉布斯自由能供应减少阻碍精神疲劳期间的大脑信息处理
Reduced Gibbs free energy supply hinders brain information processing during mental fatigue
arXiv 2608.10211 · 2026-08-12FUBU-EPSTEIN：关于杰弗里·爱泼斯坦案件及其全球公众讨论的大规模Twitter数据集（2019-2023）
FUBU-EPSTEIN: A Large-Scale Twitter Dataset on the Jeffrey Epstein Case and Its Global Public Discourse (2019-2023)
arXiv 2608.10210 · 2026-08-12评估条件化训练：让模型泛化到更强的监督机制
Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes
arXiv 2608.10209 · 2026-08-12利用强化学习结合语义站点嵌入缓解公交车扎堆问题
Mitigating Bus Bunching with Reinforcement Learning Enhanced by Semantic Stop Embedding
arXiv 2608.10207 · 2026-08-12面向儿童语音的边缘音素识别：基于年龄感知训练
Edge Phoneme Recognition for Children's Speech through Age-Aware Training
arXiv 2608.10206 · 2026-08-12MagAO-X上的传感器融合：利用加速度计实现实时振动控制
Sensor fusion on MagAO-X: real time vibration control using accelerometers
arXiv 2608.10205 · 2026-08-12面向安全强化学习的边界搜寻策略梯度算法
Boundary-Seeking Policy Gradient for Safe Reinforcement Learning
arXiv 2608.10204 · 2026-08-12用于分布外样本与对抗攻击检测方法的卷积层激活降维技术
A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods
arXiv 2608.10203 · 2026-08-12不可扩展稳定子基
Unextendible stabiliser bases
arXiv 2608.10202 · 2026-08-12面向工业应用的主动电子太赫兹成像：从硬件到人工智能驱动的范式转变
Active Electronic Terahertz Imaging for Industrial Applications: From Hardware to the Paradigm Shift by Artificial Intelligence
arXiv 2608.10200 · 2026-08-12STIS CCD的波长校准精度：管道更新与用户指南
Wavelength Calibration Accuracy Across the STIS CCD: Pipeline Update and User Guidance
arXiv 2608.10199 · 2026-08-12视觉-语言模型智能体间潜在通信的事后稀疏编码
Post-Hoc Sparse Coding of Latent Communication Between Vision-Language Model Agents
arXiv 2608.10198 · 2026-08-12含能源切换与负荷跟踪核电站的最优能源生产问题
An Optimal Energy Production Problem with Energy Source Switching and Load Following Nuclear Power Plants
arXiv 2608.10197 · 2026-08-12ELMER：探索与优化的进化语言模型
ELMER: Evolutionary Language Model that Explores and Refines
arXiv 2608.10196 · 2026-08-12更准确，更少人工：视觉模型中的格式塔分组
More Accurate, Less Human: Gestalt Grouping in Vision Models
arXiv 2608.10195 · 2026-08-12审计中的语境与对称性：以动作捕捉中的骨架推理为例
Context and Symmetry in Auditing: A Case Study of Skeleton Inference in Motion Capture
arXiv 2608.10194 · 2026-08-12适用于泥石流、泥流和浊流 regime 内粘性泥沙重力流的微连续介质物理模型
A micro-continuum physics-based model for cohesive sediment gravity flows across mudslide, mudflow, and turbidity current regimes
arXiv 2608.10192 · 2026-08-12完全正算子的积分理论：李雅普诺夫型定理及应用
Integration Theory for Completely positive Instruments: A Lyapunov-Type Theorem and Applications
arXiv 2608.10191 · 2026-08-12GPU LZ77解码的实际序列化因素：三种解码器、三种机制及一种可消除最后一种的编码时手段
What Actually Serializes GPU LZ77 Decode: Three Decoders, Three Mechanisms, and an Encode-Time Lever That Removes the Last One
arXiv 2608.10188 · 2026-08-12ConnectionMind：利用社交网络与大语言模型实现 Meta 平台的个性化推荐
ConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta
arXiv 2608.10187 · 2026-08-12审议缺陷：对大型语言模型在民主讨论中的实证批判
The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse
arXiv 2608.10186 · 2026-08-12DIY电子手碟：一种基于Arduino和ESP32微控制器的新型DIY低成本手碟界面
DIY e-HandPan: A new DIY Low-Cost Handpan Interface based on Arduino and ESP32 Microcontrollers
arXiv 2608.10185 · 2026-08-12随机椭球拟合中的尖锐可满足/不可满足（SAT/UNSAT）相变
The sharp SAT/UNSAT phase transition in random ellipsoid fitting
arXiv 2608.10184 · 2026-08-12从预测到增量性：面向大规模定向投放与推荐的因果优化
From Prediction to Incrementality: Causal Optimization for Large-Scale Targeting and Recommendation
arXiv 2608.10182 · 2026-08-12人类视觉与计算机视觉
Human versus Computer Vision
arXiv 2608.10181 · 2026-08-12构建星系的X射线双星光谱模型：X射线双星种群的贡献随宿主星系性质的变化
Constructing X-ray Spectral Models of Galaxies: Varying Contributions from X-ray Binary Populations with Host Galaxy Properties
arXiv 2608.10180 · 2026-08-12基于张量切片交换性的退化阶多项式界
Polynomial Bounds on Degeneration Order from Commutativity Properties of Tensor Slices
arXiv 2608.10179 · 2026-08-12一个方案，多种适配：自演化在不同语言和模型中编码了什么
One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models
arXiv 2608.10178 · 2026-08-12用于精细分层实验的图拉普拉斯方差估计器
Graph-Laplacian Variance Estimators for Finely Stratified Experiments
arXiv 2608.10177 · 2026-08-12TRACE：可信赖的检索增强对话引擎
TRACE: Trustworthy Retrieval-Augmented Conversational Engine
arXiv 2608.10176 · 2026-08-12超越现金流：用于临床阶段跨境生物技术估值的多智能体AI框架
Beyond Cash Flows: A Multi-Agent AI Framework for Valuing Clinical-Stage, Cross-Border Biotechnology
arXiv 2608.10175 · 2026-08-12DoseBridge：用于肺调强质子治疗剂量预测的去噪扩散桥模型
DoseBridge: Denoising Diffusion Bridge Model for Dose Prediction in Lung Intensity-Modulated Proton Therapy
arXiv 2608.10173 · 2026-08-12内在结构：机制可解释性的谱可识别性
Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
arXiv 2608.10172 · 2026-08-12用GFlowNets为大语言模型生成攻击
Generating Attacks for LLMs with GFlowNets
arXiv 2608.10171 · 2026-08-12面向3D脑部MRI运动伪影去除的感知运动伪影的自监督表示学习
Motion Artifact-Aware Self-Supervised Representation Learning for 3D Brain MRI Motion Artifact Reduction
arXiv 2608.10170 · 2026-08-12从可视化的组成颜色预测其情感内涵
Predicting affective connotation of visualizations from their constituent colors
arXiv 2608.10169 · 2026-08-12LISA中偏心旋近双星的广义相对论参数化检验
A parametrized test of general relativity for inspiralling eccentric binaries in LISA
arXiv 2608.10168 · 2026-08-12常规色散解监测得到的CCD旋转率
CCD Rotation Rates From Regular Dispersion Solution Monitoring
arXiv 2608.10167 · 2026-08-12
