2026-07论文中文摘要
多用户多输入单输出系统中用于直接导频到波束成形器设计的自进化上下文学习
Self-Evolving In-Context Learning for Direct Pilot-to-Beamformer Design in MU-MISO Systems
arXiv 2607.11970 · 2026-07-15纠缠量子态的双协方差模型：高斯约简到二阶协方差
Double Covariance Model for Entangled Quantum States: Gaussian Reduction to Second Order Covariances
arXiv 2607.11968 · 2026-07-15超越坐标规范：神经坍缩后检测供体特异性功能指纹的审核协议
Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse
arXiv 2607.11967 · 2026-07-15扩展天体物理热核函数的闭式表示
Closed-form representations of extended astrophysical thermonuclear functions
arXiv 2607.11966 · 2026-07-15LIDAR-AD：一种用于自动驾驶的无解码器潜在交互梦想家与动作残差链
LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving
arXiv 2607.11964 · 2026-07-15评估用于早期慢性肾病预测的机器学习模型的可靠性：数据泄露和预测器稳定性的系统综述
Evaluating Reliability in Machine Learning Models for Early Chronic Kidney Disease Prediction: A Systematic Review of Data Leakage and Predictor Stability
arXiv 2607.11963 · 2026-07-15用于结构MRI中表示学习的对比联合嵌入预测
Contrastive Joint-Embedding Prediction for Representation Learning in Structural MRI
arXiv 2607.11962 · 2026-07-15KRAFT：一个集成了上下文指标的韩国公寓销售交易级数据集
KRAFT: A Transaction-Level Dataset for Korean Apartment Sales Integrated with Contextual Indicators
arXiv 2607.11961 · 2026-07-15具有布洛赫型感知记忆的认知群体智能体中的自愈协调
Self-Healing Coordination in Cognitive Swarm Agents with Bloch-Type Perceptual Memory
arXiv 2607.11960 · 2026-07-15智能温室强化学习控制中的校准优先奖励组件审计
Calibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses
arXiv 2607.11959 · 2026-07-15建构的现实，有争议的先验：解耦与自由能原理下认知复发的架构
Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle
arXiv 2607.11958 · 2026-07-15用于极端临床代码预测的图约束策略学习
Graph-Constrained Policy Learning for Extreme Clinical Code Prediction
arXiv 2607.11954 · 2026-07-15用于网络对齐的可扩展最优传输算法
Scalable Optimal Transport Algorithm for Network Alignment
arXiv 2607.11952 · 2026-07-15GRID：用于企业SQL生成的语法约束解码
GRID: Grammar-Railed Decoding for Enterprise SQL Generation
arXiv 2607.11951 · 2026-07-15BAT-RM：一种用于临床部署的宫颈癌放疗自动轮廓勾画的具有区域感知多向曼巴的边界感知变换器
BAT-RM: A Boundary-Aware Transformer with Region-Aware Multi-Directional Mamba for Clinically Deployed Cervical Cancer Radiotherapy Auto-Contouring
arXiv 2607.11949 · 2026-07-15主权企业语言模型的本体增强蒸馏与上下文审查：机制验证与负面结果的组合方法研究
Ontology-Amplified Distillation and Contextuality Auditing for Sovereign Enterprise Language Models: A Combined Proof-of-Mechanism and Negative-Results Method Study
arXiv 2607.11948 · 2026-07-15用于低资源澳大利亚原住民语言识别的混合持续学习
Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification
arXiv 2607.11946 · 2026-07-15MAGE：理解多组件提示优化中的稳定性-性能权衡
MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization
arXiv 2607.11944 · 2026-07-15BattVAE-GP：具有不确定性量化的长周期电池退化生成建模
BattVAE-GP: Generative Modeling of Long-Horizon Battery Degradation with Uncertainty Quantification
arXiv 2607.11943 · 2026-07-15查询可见性如何改变键值缓存压缩排名：匹配预算审计
How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit
arXiv 2607.11942 · 2026-07-15GenDiff：一种具有结构先验细化的剂量和解剖感知扩散模型，用于低剂量CT重建和泛化
GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization
arXiv 2607.11941 · 2026-07-15CARE-LoRA：用于内存高效LoRA的压缩激活重建
CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA
arXiv 2607.11940 · 2026-07-15TSCA-Net：用于可解释多模态行人轨迹预测的时空团块注意力
TSCA-Net: Temporal-Spatial Clique Attention for Interpretable Multimodal Pedestrian Trajectory Prediction
arXiv 2607.11939 · 2026-07-15数据科学的数学
Mathematics of Data Science
arXiv 2607.11938 · 2026-07-15镜像视界：作为有界反射度量的可行路径熵
Mirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection
arXiv 2607.11937 · 2026-07-15通过对数编码实现用于超维分解的量子比特高效量子搜索
Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding
arXiv 2607.11936 · 2026-07-15特征向量旋转先于基于特征值的早期预警信号：一种用于检测临界转变的时变参数卡尔曼方法
Eigenvector rotation precedes eigenvalue-based early-warning signals: a TVP-Kalman approach to detecting critical transitions
arXiv 2607.11935 · 2026-07-15广义q-摩根·沃伊斯多项式
Generalized q-Morgan Voyce Polynomials
arXiv 2607.11934 · 2026-07-15通过知识蒸馏将语言模型转换为高效的交叉编码器用于RAG重排
Transforming LLMs into Efficient Cross-Encoders via Knowledge Distillation for RAG Reranking
arXiv 2607.11933 · 2026-07-15加权拓扑中的近似单调性、次可加性和凸性
Approximate monotonicity, subadditivity, and convexity in weighted topologies
arXiv 2607.11932 · 2026-07-15自我指涉测试
Self-Referential Tests
arXiv 2607.11930 · 2026-07-15利用介质表面上电磁模拟偶极天线量化黑暗时代21厘米功率谱中的前景污染
Quantifying Foreground Contamination in the Dark Ages 21 cm Power Spectrum Using an Electromagnetically Simulated Dipole Antenna Atop a Dielectric Surface
arXiv 2607.11929 · 2026-07-15修复远距离单次条纹投影轮廓术中的形状先验捷径
Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
arXiv 2607.11928 · 2026-07-15模糊李群上的哈尔测度
Haar Measure on Fuzzy Lie Group
arXiv 2607.11927 · 2026-07-15无平方因子层数的布尔沃尔什埃塔单位与艾森斯坦基
Boolean Walsh Eta Units and Eisenstein Bases For Squarefree Levels
arXiv 2607.11926 · 2026-07-15计算拼图组装的连通和非连通方式
Counting Connected and Disconnected Ways to Assemble a Jigsaw Puzzle
arXiv 2607.11923 · 2026-07-15模拟布伦特原油价格与尼泊尔证券交易所之间的动态关系：一种计量经济学与可解释机器学习的综合方法
Modeling the Dynamic Relationship Between Brent Crude Oil Prices and the Nepal Stock Exchange: An Integrated Econometric and Explainable Machine Learning Approach
arXiv 2607.11922 · 2026-07-15高斯索伯列夫算子的近最优学习
Near-Optimal Learning of Gaussian Sobolev Operators
arXiv 2607.11921 · 2026-07-15对主观预期效用最大化的敏感性：一项方法学研究，并应用于大语言模型决策
Sensitivity to Subjective Expected Utility Maximization: A Methodological Study, with an Illustrative Application to LLM Decision-Making
arXiv 2607.11920 · 2026-07-15你还记得吗？迈向以记忆为中心的多模态人工智能
Do You Remember? Toward Memory-Centric Multimodal AI
arXiv 2607.11919 · 2026-07-15AAAI-26双重投稿：新挑战
AAAI-26 Dual Submissions: Novel Challenges
arXiv 2607.11918 · 2026-07-15利用平方公里阵列天文台超越ΛCDM——I：在宇宙学尺度上探测引力
Beyond ΛCDM with the SKA Observatory -- I: Probing Gravity on Cosmological Scales
arXiv 2607.11917 · 2026-07-15QDEvo：用于自动启发式设计的多目标质量多样性框架
QDEvo: A Multi-Objective Quality-Diversity Framework for Automated Heuristic Design
arXiv 2607.11916 · 2026-07-15托卡马克等离子体诊断模型中的传感器鲁棒性基准测试：对托卡马克的系统评估
Benchmarking Sensor Robustness in Plasma Diagnostic Models: A Systematic Evaluation on TokaMark
arXiv 2607.11915 · 2026-07-15突发脉冲神经网络
Burst Spiking Neural Networks
arXiv 2607.11914 · 2026-07-15迈向自我进化智能体：一种受人类启发的遗传网络编程自适应探索-利用框架
Towards Self-Evolving Agents: A Human-Inspired Adaptive Exploration-Exploitation Framework for Genetic Network Programming
arXiv 2607.11913 · 2026-07-15关于量子环境不变性和交换对称性的统计力学评论
Comment on Statistical mechanics from quantum envariance and exchange symmetry
arXiv 2607.11912 · 2026-07-15关于温度变化可解决多伊奇 - 约扎问题：热力学查询复杂度的探索
Comment on Temperature change can solve the Deutsch-Jozsa problem: An exploration of thermodynamic query complexity
arXiv 2607.11911 · 2026-07-15SeqGPT：用于多面板复合结构逆向设计的受限Transformer智能体
SeqGPT: A Constrained Transformer Agent for the Inverse Design of Multi-Panel Composite Structures
arXiv 2607.11910 · 2026-07-15成为量子计算机是什么样的：封闭量子全局工作空间——作为希尔伯特空间中关联动力学的意识访问与整合
What It Is Like To Be A Quantum Computer: A Closed Quantum Global Workspace -- Conscious Access and Integration as Correlation Dynamics in Hilbert Space
arXiv 2607.11909 · 2026-07-15
