2026-09论文中文摘要
学习利用通用恢复先验进行偏振图像恢复
Learning Polarization Image Restoration with General Restoration Priors
arXiv 2609.30728 · 2026-09-28深度伪近端映射：一种用于迭代重建的自监督数据拟合代理
Deep Pseudo-Proximal Map: A Self-Supervised Data-Fitting Agent for Iterative Reconstruction
arXiv 2609.30727 · 2026-09-28几乎正交的Strichartz估计与径向改进
Almost-orthogonal Strichartz estimates and radial improvements
arXiv 2609.30726 · 2026-09-28EviDETR：保留查询相关时间证据用于时刻检索与高亮检测
EviDETR: Preserving Query-Relevant Temporal Evidence for Moment Retrieval and Highlight Detection
arXiv 2609.30724 · 2026-09-28大规模并网逆变器资源的并发参数学习与电流控制
Concurrent Parameter Learning and Current Control for Large-scale Grid-following Inverter-based Resources
arXiv 2609.30723 · 2026-09-28TrafficImag：用于反事实路侧交通视频生成的基准
TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation
arXiv 2609.30722 · 2026-09-28当10000个窗口并非10000次测试：审计滑动窗口时间序列分类中的统计置信度
When 10,000 Windows Are Not 10,000 Tests: Auditing Statistical Confidence in Sliding-Window Time-Series Classification
arXiv 2609.30721 · 2026-09-28多视图张量观测的最优个性化子空间学习
Optimal Personalized Subspace Learning for Multi-view Tensor Observations
arXiv 2609.30720 · 2026-09-28Werracle：用于EVM智能合约的亚中心块内AI反射预言机与闪电贷断路器
Werracle: Sub-Cent Intra-Block AI Reflex Oracles and Flash-Loan Circuit Breakers for EVM Smart Contracts
arXiv 2609.30719 · 2026-09-28NEMSim：通过可执行事件-机制先验学习控制条件下的多事件物理动力学
NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors
arXiv 2609.30718 · 2026-09-28词胜于序：Gemma 4 的行为评估
Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4
arXiv 2609.30716 · 2026-09-28RoboMonitor：通过预测性表示学习实现机器人任务执行的标签高效运行时监控
RoboMonitor: Label-Efficient Runtime Monitoring of Robot Task Execution via Predictive Representation Learning
arXiv 2609.30715 · 2026-09-28CRC-Router：面向医疗智能体AI系统的风险约束路由
CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems
arXiv 2609.30714 · 2026-09-28基于经验局部化变形Bregman散度的非归一化离散模型参数估计
Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence
arXiv 2609.30713 · 2026-09-28析取子模函数：包络及其在库存与0-1二次优化中的应用
Disjunctive Submodular Functions: Envelopes and Applications to Inventory and 0-1 Quadratic Optimization
arXiv 2609.30712 · 2026-09-28推荐世界模型用于未来状态控制
Recommendation World Models for Future-State Control
arXiv 2609.30711 · 2026-09-28高自旋同核异能态中的一种新型皮厚度用于约束自旋极化核物质的状态方程
A new type of skin thickness in high-spin isomers to constrain equation of state of spin-polarized nuclear matter
arXiv 2609.30710 · 2026-09-28VLALight：面向紧急感知交通信号控制的轻量级视觉-语言-动作模型
VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control
arXiv 2609.30709 · 2026-09-28结合通用与领域特定预文本任务的脑部MR图像分割
Combining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation
arXiv 2609.30708 · 2026-09-28一种用于带Radon测度追踪和逐点控制约束的Darcy最优控制的单片间断Galerkin框架
A Monolithic Discontinuous Galerkin Framework for Darcy Optimal Control with Radon-Measure Tracking and Pointwise Control Constraints
arXiv 2609.30707 · 2026-09-28LAVOIR：教单遍决策编码器何时询问以及询问什么——基于摊销信息价值
LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information
arXiv 2609.30706 · 2026-09-28思考的代价：测试时推理在LLM交易中是否值得？
The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?
arXiv 2609.30705 · 2026-09-28从视觉搜索到运动控制：人工代理的优先级场
From Visual Search to Movement Control: A Priority Field for Artificial Agents
arXiv 2609.30704 · 2026-09-28SAGE：基于频率均衡的源锚定引导用于层级RGB-T对齐与融合
SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion
arXiv 2609.30703 · 2026-09-28从双边贸易到匹配市场：贸易收益的显著提升
From Bilateral Trade to Matching Markets: Sharp Gains from Trade
arXiv 2609.30702 · 2026-09-28透镜化热点图像中的传播延迟与区域强度变化
Propagation delays and regional intensity changes in lensed hotspot images
arXiv 2609.30701 · 2026-09-28度量测度空间的粗几何
Coarse geometry of metric measure spaces
arXiv 2609.30700 · 2026-09-28“如果你不做，别人就会做”：主动协商与持续使用LLM的无形劳动
"If You're Not Doing It, Somebody Else Is": Active Negotiation and the Invisible Labor of Sustained LLM Use
arXiv 2609.30699 · 2026-09-28MM-VeriAgent：通过强化学习学会使用多种工具验证多模态虚假信息
MM-VeriAgent: Learning to Use Extensive Tools to Verify Multimodal Misinformation with Reinforcement Learning
arXiv 2609.30698 · 2026-09-28第二基本形式范数恒定的自收缩子的第二间隙
The second gap for self-shrinkers with constant norm of the second fundamental form
arXiv 2609.30697 · 2026-09-28基于视觉的敏捷间隙穿越学习：带暖启动评论家的可微分仿真
Learning Vision-Based Agile Gap Traversal: Differentiable Simulation with a Warm-Started Critic
arXiv 2609.30696 · 2026-09-28下肢外骨骼的多目标人在回路贝叶斯优化
Multi-Objective Human-in-the-Loop Bayesian Optimization of a Lower-Limb Exoskeleton
arXiv 2609.30695 · 2026-09-28基于SpeechLLM的错误感知选择性检索的无训练上下文语音识别
Training-Free Contextual ASR via SpeechLLM-Based Error-Aware Selective Retrieval
arXiv 2609.30694 · 2026-09-28消失黏性 Hamilton-Jacobi 方程周期均匀化中的收敛速率
Convergence rates in the periodic homogenization of vanishing-viscous Hamilton-Jacobi equations
arXiv 2609.30693 · 2026-09-28LUMO（轻量级统一多语言编排器）：一种隐私保护的离线语音助手
LUMO (Lightweight Unified Multilingual Orchestrator): A Privacy Preserving Offline Voice Assistant
arXiv 2609.30692 · 2026-09-28ADF-EA：面向智能体设备基础的一种统一执行保障系统
ADF-EA: A Unified Execution Assurance System for Agent Device Foundation
arXiv 2609.30691 · 2026-09-28威胁感知的能耗高效动态无人机网络部署：一种多智能体强化学习方法
Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach
arXiv 2609.30690 · 2026-09-28评注：关于“对称伪随机矩阵”
Comment on "Symmetric Pseudo-Random Matrices"
arXiv 2609.30689 · 2026-09-28单变量深度学习在有效波高预报中的局限性研究
On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting
arXiv 2609.30688 · 2026-09-28水平海床运动产生的完全非线性波下的粒子轨迹
Particle Trajectories Beneath Fully Nonlinear Waves Generated by Horizontal Seabed Motion
arXiv 2609.30687 · 2026-09-28一种基于2D自相关的频率估计器，反映空间组织分布以改进超声H-scan组织表征
A 2D autocorrelation-based frequency estimator reflecting spatial tissue distribution to improve Ultrasound H-scan tissue characterization
arXiv 2609.30686 · 2026-09-28非紧流形乘积上的正标量曲率
Positive scalar curvature on products of noncompact manifolds
arXiv 2609.30685 · 2026-09-28PixSim：一个在分析师容量约束下模拟即时支付欺诈、追回与拦截的校准开源模拟器
PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraints
arXiv 2609.30684 · 2026-09-28现代钓鱼邮件内容的大规模实证研究
A Large-Scale Empirical Study of Modern Phishing Email Content
arXiv 2609.30683 · 2026-09-28结构引导的掩码自编码器用于超高分辨率科学图像理解
Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding
arXiv 2609.30682 · 2026-09-28双调和非线性薛定谔方程的长时约化
Long-time reduction for the biharmonic nonlinear Schrödinger equation
arXiv 2609.30681 · 2026-09-28流行病学中忽略设计与尊重设计的世界模型
Design-Ignoring versus Design-Respecting World Models for Epidemiology
arXiv 2609.30679 · 2026-09-28基于蒙特卡洛零阶梯度估计的仿真高效模拟电路良率优化
Simulation-Efficient Analog Circuit Yield Optimization via Monte Carlo Zeroth-Order Gradient Estimation
arXiv 2609.30678 · 2026-09-28全体积迈斯纳效应超导BKBO晶体的电化学生长
Electrochemical Growth of Full Volume Meissner Effect Superconducting BKBO
arXiv 2609.30677 · 2026-09-28机器人能读盲文吗？——通过模仿学习自适应接触以实现触觉盲文识别
Can a Robot Read Braille? - Learning to Adapt Contact via Imitation Learning for Tactile Braille Recognition
arXiv 2609.30676 · 2026-09-28
