2026-10论文中文摘要
针对基于VLM的AI生成图像检测的排版攻击
Typographic Attack Against VLM-based AI-generated Image Detection
arXiv 2609.39662 · 2026-10-01大型语言模型中注意力的演变：机制、权衡与新兴趋势
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
arXiv 2609.39661 · 2026-10-01BAM! 贝叶斯任意模型：用于生成式计算成像的基础模型
BAM! Bayesian Anything Model: a foundation model for generative computational imaging
arXiv 2609.39660 · 2026-10-01矩阵谱序的Grassmann公式
A Grassmann formula for the spectral order of matrices
arXiv 2609.39659 · 2026-10-01图残差共轭扩散：面向图信号的SNR均衡热流
Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals
arXiv 2609.39658 · 2026-10-01结构无关蒸馏的可扩散潜变量
Diffusable Latents from Structure-Agnostic Distillation
arXiv 2609.39657 · 2026-10-01外平面图中随机邻居预言机下的导出子图自由性测试
Testing Induced-Subgraph Freeness in Outerplanar Graphs under the Random-Neighbor Oracle
arXiv 2609.39656 · 2026-10-01关于伪零模的商
On the Quotient of a Pseudo-null Module
arXiv 2609.39655 · 2026-10-01质子-质子碰撞中 Z+jet 产生的三重微分截面在 $\sqrt{s}$ = 13 TeV 下的测量
Measurement of the triple-differential cross section of Z+jet production in proton-proton collisions at $\sqrt{s}$ = 13 TeV
arXiv 2609.39653 · 2026-10-01制造波澜：一种膜耦合 Delta 阵列，用于操控执行器间距以下的物体
Making Waves: A Membrane-Coupled Delta Array for Manipulating Objects Below the Actuator Spacing
arXiv 2609.39652 · 2026-10-01用于稳健音频深度伪造检测的神经音频编解码器
Neural Audio Codec for Robust Audio Deepfake Detection
arXiv 2609.39651 · 2026-10-01FANVIDv2：在复合退化下通过人脸和车牌识别评估视频超分辨率
FANVIDv2: Evaluating Video Super-Resolution by Face and Licence-Plate Recognition Under Compound Degradation
arXiv 2609.39649 · 2026-10-01从模态到记忆：刻画扩散模型的尺度空间动力学
From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models
arXiv 2609.39648 · 2026-10-01光前夸克模型中的衍射矢量介子产生
Diffractive Vector-Meson Production from the Light-Front Quark Model
arXiv 2609.39647 · 2026-10-01超越均匀压缩：极端联邦学习中的预算化传输分配
Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated Learning
arXiv 2609.39646 · 2026-10-01SEPAL：分离专家对与答案级融合实现可靠的LLM协作
SEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM Collaboration
arXiv 2609.39645 · 2026-10-01原子位错模型分析中的线性化力平衡条件
On the linearised force balance condition in the analysis of atomistic dislocation models
arXiv 2609.39642 · 2026-10-01零计算跨语言迁移性估计：基于类型学特征代理
Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies
arXiv 2609.39640 · 2026-10-01边际响应面启发用于零标签表格学习
Marginal Response Surface Elicitation for Zero-Label Tabular Learning
arXiv 2609.39639 · 2026-10-01预测优于检测：利用无人机进行交通拥堵控制
Prediction is Better than Detection: Traffic Congestion Control using Drones
arXiv 2609.39637 · 2026-10-01平面各向同性$L_p$对偶Minkowski问题非恒定正解的精确个数
The exact number of nonconstant positive solutions to the planar isotropic $L_p$ dual Minkowski problem
arXiv 2609.39636 · 2026-10-01SAGE：基于视觉基础表征的显著因子发现与生成
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
arXiv 2609.39635 · 2026-10-01路径上随机可堆叠性的固定偏移转变
A Fixed-Offset Transition for Random Stackability on Paths
arXiv 2609.39633 · 2026-10-01Kirin：云原生WebAssembly服务编排
Kirin: Cloud-native WebAssembly Service Orchestration
arXiv 2609.39631 · 2026-10-01PEG-Tab：表格合成中的采样时间记录修复与发布控制
PEG-Tab: Sampling-Time Record Repair and Release Control for Tabular Synthesis
arXiv 2609.39630 · 2026-10-01基于认证的差分隐私学习
Certification-Based Differentially Private Learning
arXiv 2609.39629 · 2026-10-01MIND：面向混合类型表格生成的边际不变神经依赖扩散模型
MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generation
arXiv 2609.39628 · 2026-10-01计算机视觉导论
Introduction to Computer Vision
arXiv 2609.39627 · 2026-10-01基于StyleGAN中间潜空间的地质参数化方法用于集成数据同化
Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN
arXiv 2609.39626 · 2026-10-01D-Scope：利用稀疏自编码器分解和引导扩散Transformer
D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
arXiv 2609.39625 · 2026-10-01ExpandDiff：用于单图像HDR重建的动态范围扩展扩散模型
ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction
arXiv 2609.39624 · 2026-10-01面向恶意图像篡改检测的语义水印
Semantic Watermarking for Malicious Image Manipulation Detection
arXiv 2609.39623 · 2026-10-01Fock 空间中 Korenblum 最大值原理的精确半径
The sharp radius in Korenblum's maximum principle for the Fock space
arXiv 2609.39622 · 2026-10-01弱测量循环用于量子振幅放大：预言机节省与未知目标概率下的自适应搜索
Weakly Measured Loops for Quantum Amplitude Amplification: Oracle Savings and Adaptive Search with Unknown Target Probability
arXiv 2609.39621 · 2026-10-01Kahler-Ricci流的Type I估计 I
Type I estimates for the Kahler-Ricci flow I
arXiv 2609.39620 · 2026-10-01某些无限毛毛虫族的亚法定人数染色
Sub-quorum colorings of some infinite families of caterpillars
arXiv 2609.39619 · 2026-10-01TO-mdiSPAs：多方向软体气动执行器的拓扑优化
TO-mdiSPAs: Topology Optimization of multi-directional Soft Pneumatic Actuators
arXiv 2609.39618 · 2026-10-01$(α, β)$ 生成子图与近紧界的混合生成子图
$(α, β)$ Spanners and Hybrid Spanners with Nearly Tight Bounds
arXiv 2609.39617 · 2026-10-01深度截断FBSDE方法：高维非线性PDE和全耦合FBSDE的稳健求解器
Deep Truncated FBSDE Method: A Robust Solver for High-Dimensional Nonlinear PDEs and Fully Coupled FBSDEs
arXiv 2609.39616 · 2026-10-01有限空间的弱、稳定和普通Lusternik-Schnirelmann范畴
Weak, stable, and ordinary Lusternik-Schnirelmann category of finite spaces
arXiv 2609.39615 · 2026-10-01改进James-Stein估计量：通过其正部的有限和截断
Improving the James-Stein estimator via finite-sum truncation of its positive-part
arXiv 2609.39614 · 2026-10-01用于稳健表格数据插补的混合方法
Hybrid Methods for Robust Tabular Data Imputation
arXiv 2609.39613 · 2026-10-01迈向基于视觉的敏捷多无人机飞行：重新审视状态估计
Towards Agile Vision-Based Multi-UAV Flight: Revisiting State Estimation
arXiv 2609.39611 · 2026-10-01基于电路的具有狄拉克特性的周期性十字形单元色散分析
Circuit-Based Dispersion Analysis of Periodic Cross-Shaped Unit Cells with Dirac Characteristics
arXiv 2609.39610 · 2026-10-01这是决策关键证据吗？学习验证规则治理决策
Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions
arXiv 2609.39608 · 2026-10-01FOMO：在选择性视频遗忘中遗忘概念，不错过场景
FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning
arXiv 2609.39605 · 2026-10-01为什么传统世界模型无法学习元胞自动机？
Why Do Conventional World Models Fail to Learn Cellular Automata?
arXiv 2609.39604 · 2026-10-01基于支路交换编码的暖启动迭代QITE用于配电网重构
Warm-Start Iterative QITE for Distribution Network Reconfiguration via Branch-Exchange Encoding
arXiv 2609.39602 · 2026-10-01GroundingPI：面向物理智能的基于视觉基元的接地基础模型
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
arXiv 2609.39601 · 2026-10-01GroundAnything：以闪电速度调和并行解码与精确视觉定位
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
arXiv 2609.39600 · 2026-10-01
