2026-07论文中文摘要
利用约束柯尔莫哥洛夫 - 阿诺德网络对积分 - 微分方程中的记忆和非局部核进行神经发现
Neural Discovery of Memory and Nonlocal Kernels in Integro-Differential Equations with Constrained Kolmogorov--Arnold Networks
arXiv 2607.11110 · 2026-07-14生成式中文法规检索
Generative Chinese Statute Retrieval
arXiv 2607.11109 · 2026-07-14从三维拓扑量子场论视角看卫星构造与环面分解
A TQFT perspective on satellite constructions and toral decompositions
arXiv 2607.11108 · 2026-07-14一种通过分组属性补全和置信度感知对比学习的新型图欺诈检测器
A Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware Contrastive Learning
arXiv 2607.11107 · 2026-07-14超越视觉：通过自我调节的隐式视觉工具实现高效多模态推理
Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools
arXiv 2607.11106 · 2026-07-14平铺分解多重性预测GaN(0001)表面重构的稳定性
Tiling decomposition multiplicity predicts stability of GaN(0001) surface reconstructions
arXiv 2607.11105 · 2026-07-14FlowPET：用于低计数PET重建的物理信息辛流匹配
FlowPET: Physics-Informed Symplectic Flow Matching for Low-Count PET Reconstruction
arXiv 2607.11104 · 2026-07-14在NLT中开发并验证局部新经典输运模块及其在与EAST相关的杂质输运和捕获电子模稳定性中的应用
Development and validation of a local neoclassical transport module in NLT with applications to EAST-relevant impurity transport and trapped-electron-mode stability
arXiv 2607.11103 · 2026-07-14CHARM：基于大语言模型的多模态讽刺检测中的电荷校准与声学救援
CHARM: Charge Calibration and Acoustic Rescue for LLM-based Multimodal Sarcasm Detection
arXiv 2607.11102 · 2026-07-14在阿贝尔幂零根基上自由的\(\mathfrak{so}_n(\mathbb{C})\) - 模
$\mathfrak{so}_n(\mathbb{C})$-modules which are free over an abelian nilradical
arXiv 2607.11100 · 2026-07-14重新审视用于宽基线全向立体视觉的匹配响应和扫描特征体
Revisiting Matching Response and Swept Feature Volumes for Wide-baseline Omnidirectional Stereo
arXiv 2607.11097 · 2026-07-14差异驱动门控：U-Net 解码器的自适应特征融合
Difference-Driven Gating: Adaptive Feature Fusion for U-Net Decoder
arXiv 2607.11096 · 2026-07-14当廉价梯度失效时：攻击量子分类器的测量成本
When cheap gradients fail: the measurement cost of attacking quantum classifiers
arXiv 2607.11095 · 2026-07-14达到赫佐格 - 熊代 - 斯塔马特界的远距戈伦斯坦数值半群的存在性
Existence of a far-flung Gorenstein numerical semigroup attaining the Herzog--Kumashiro--Stamate bound
arXiv 2607.11093 · 2026-07-14通过SPD几何在非参数指数统计流形上的可处理伪度量
A Tractable Pseudo-Metric on Non-Parametric Exponential Statistical Manifolds via SPD Geometry
arXiv 2607.11092 · 2026-07-14使证据神经网络适应测试时的邻居融合可改善分子性质预测
Adapting Evidential Neural Networks to Test-Time Neighbor Fusion Improves Molecular Property Prediction
arXiv 2607.11091 · 2026-07-14为何低光相机出现色盲现象：去除原始图像去噪中的颜色偏差
Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising
arXiv 2607.11090 · 2026-07-14OS-Pruner：通过最优停止修剪推理模型的思维链
OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping
arXiv 2607.11089 · 2026-07-14CUST：用于轻量级图像超分辨率的聚类单元级相似性变换器
CUST: Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution
arXiv 2607.11088 · 2026-07-14能量演算：计算系统中能量的组合代数
Energy Calculus: A Compositional Algebra of Energy in Computational Systems
arXiv 2607.11087 · 2026-07-14重新思考MCP安全性：对运行时MCP服务器和安全扫描器可靠性的大规模研究
Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability
arXiv 2607.11086 · 2026-07-14罗塔 - 巴克斯特李\(H -\)伪代数的高阶结构
Higher Structures of Rota--Baxter Lie $H$-Pseudoalgebras
arXiv 2607.11085 · 2026-07-14NVAITC人工智能科学家：一个受治理的端到端研究系统——以高血压全基因组关联研究为例
NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study
arXiv 2607.11084 · 2026-07-14用于 REAL-TSE 挑战赛的 SonicAGI 系统
The SonicAGI System for the REAL-TSE Challenge
arXiv 2607.11083 · 2026-07-14实缝合希盖尔弗勒同调
Real sutured Heegaard Floer homology
arXiv 2607.11082 · 2026-07-14通过注意力头控制扩散变换器中的运动传递
Controlling Motion Transfer in Diffusion Transformers via Attention Heads
arXiv 2607.11081 · 2026-07-14利用盖亚DR3视差和近红外测光法估计五个博克球状体的距离：用三维尘埃图进行验证
Distance Estimates to Five Bok Globules Using Gaia DR3 Parallaxes and Near-Infrared Photometry: Validation with 3D Dust Maps
arXiv 2607.11080 · 2026-07-14大语言模型准备好进行科学发现了吗？面向能力的人工智能科学家基准测试
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists
arXiv 2607.11079 · 2026-07-14视频语言模型真的在观看吗？诊断长视频中的角色跟踪失败
Do Video-LLMs Actually Watch? Diagnosing Character-Tracking Failures in Long-Form Video
arXiv 2607.11078 · 2026-07-14退火温度对近2:1:1比例的共溅射Fe-Mn-Sn薄膜结构和性能的影响
Effect of annealing temperature on the structure and properties of co-sputtered Fe-Mn-Sn films near 2:1:1 ratio
arXiv 2607.11077 · 2026-07-14由分数布朗运动驱动的随机微分方程的斯莫卢霍夫斯基-克莱默斯近似
Smoluchowski-Kramers Approximation for Stochastic Differential Equations driven by Fractional Brownian Motion
arXiv 2607.11076 · 2026-07-14使用联合汤普森采样的链路自适应
Link Adaptation Using Joint-Thompson Sampling
arXiv 2607.11075 · 2026-07-14ResearchQA：科学论文中基于引用的问答基准测试
ResearchQA: Benchmarking Citation-Grounded Question-Answering on Scientific Papers
arXiv 2607.11074 · 2026-07-14AeroMELD：用于诊断和潜在动力学的气溶胶群体线性嵌入
AeroMELD: A Linear Embedding of Aerosol Populations for Diagnostics and Latent Dynamics
arXiv 2607.11073 · 2026-07-14基于神经网络的双侧供电铁路系统阻抗识别与稳定性分析
Neural Network-Based Impedance Identification and Stability Analysis for Double-Sided Feeding Railway Systems
arXiv 2607.11072 · 2026-07-14DDR-Net：用于单图像去雾的雾感知双域细化
DDR-Net: Haze-Aware Dual-Domain Refinement for Single-Image Dehazing
arXiv 2607.11071 · 2026-07-14MJ：通过分解信用分配实现多轮语言模型越狱
MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment
arXiv 2607.11070 · 2026-07-14尖锐三元鞅等周性与\(n\)进 Takagi 型下界
Sharp Ternary Martingale Isoperimetry and $n$-adic Takagi-Type Lower Bounds
arXiv 2607.11069 · 2026-07-14模素数的连续二次剩余和非剩余模式的精确频率
Exact Frequencies of Consecutive Quadratic Residue and Nonresidue Patterns Modulo a Prime
arXiv 2607.11068 · 2026-07-14关于\(\sigma_2\)-Yamabe方程的爆破现象
Blow-up phenomena for the $σ_2$-Yamabe equation
arXiv 2607.11067 · 2026-07-14用于基于表面肌电信号的肌肉疲劳检测的高效且鲁棒的脉冲神经网络
Efficient and Robust Spiking Neural Networks for sEMG-Based Muscle Fatigue Detection
arXiv 2607.11065 · 2026-07-14WiFi-JEPA：用于WiFi-CSI 3D人体姿态估计的自监督学习
WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation
arXiv 2607.11064 · 2026-07-14电气化铁路-电网混合不对称耦合系统的潮流模型及其线性化方法
A Flow Model for the Electrified Railway-Power Grid Hybrid Asymmetric Coupled System and its Linearized Method
arXiv 2607.11060 · 2026-07-14基于神经网络从X射线磁圆二色光谱重建自旋和轨道角动量
Neural-network-based reconstruction of spin and orbital angular momentum from X-ray magnetic circular dichroism spectra
arXiv 2607.11058 · 2026-07-14通过德恩手术得到双曲三维流形的一般性
Genericity of hyperbolic 3-manifolds via Dehn surgery
arXiv 2607.11057 · 2026-07-14约束凸-凹极小极大问题单环随机方法的最后迭代收敛性
Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems
arXiv 2607.11056 · 2026-07-14朴素分散投资何时有效及为何有效：一种简单的诊断策略
When and Why Naïve Diversification Works: A Simple Diagnostic Strategy
arXiv 2607.11054 · 2026-07-14自担风险：在认知不对称下大语言模型在语用合作方面存在困难
Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry
arXiv 2607.11053 · 2026-07-14领域感知缩放定律揭示数据协同效应
Domain-Aware Scaling Laws Uncover Data Synergy
arXiv 2607.11052 · 2026-07-14有界区域中一类 Neumann 边界条件下梯度型薛定谔系统的归一化解
Normalized solutions for a class of gradient-type Schrödinger systems under Neumann boundary conditions in bounded domains
arXiv 2607.11051 · 2026-07-14
