2026-09论文中文摘要
对称积的 $L$-类：一个同调公式
$L$-classes of symmetric products: a homological formula
arXiv 2609.32793 · 2026-09-29理解并利用训练后阶段中的各向异性
Understanding and Exploiting Anisotropy in Post-Training
arXiv 2609.32792 · 2026-09-29FedHV：用于联邦多目标优化的低开销超体积加权
FedHV: Low-Overhead Hypervolume Weighting for Federated Multi-Objective Optimization
arXiv 2609.32790 · 2026-09-29大规模点云的隐式几何表示的分层频域压缩
Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds
arXiv 2609.32789 · 2026-09-29Getting Motif-ated: 从注入的动机提示中可控地生成AI音乐作品
Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts
arXiv 2609.32788 · 2026-09-29CLAIRE：一种面向医疗行政表单填写的模式引导混合工作流
CLAIRE: A Schema-Grounded Hybrid Workflow for Healthcare Administrative Form Completion
arXiv 2609.32787 · 2026-09-29有限集合的Čech复形
Čech complexes for finite sets
arXiv 2609.32786 · 2026-09-29学习何时递归：面向不平衡眼科领域增量学习的令牌自适应递归
Learning When to Recur: Token-Adaptive Recursion for Imbalanced Ophthalmic Domain Incremental Learning
arXiv 2609.32785 · 2026-09-29交换代数是进化代数的理想
Commutative algebras are ideals of evolution algebras
arXiv 2609.32784 · 2026-09-29CollisionGAT：用于多智能体运动的控制器无关单步碰撞筛查
CollisionGAT: Controller-Agnostic One-Step Collision Screening for Multi-Agent Motion
arXiv 2609.32783 · 2026-09-29学习响应感知的患者动力学以支持呼吸治疗
Learning response-aware patient dynamics for respiratory support
arXiv 2609.32782 · 2026-09-29CT-OPD：用于扩散视觉语言模型的反事实轨迹在策略蒸馏
CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models
arXiv 2609.32781 · 2026-09-29OmniMoE-VL：一种具有耦合视觉-深度路由的稀疏视觉-语言模型
OmniMoE-VL: A Sparse Vision-Language Model with Coupled Visual-Depth Routing
arXiv 2609.32780 · 2026-09-29Copper-Policy：聚焦表示以实现稳健的机器人操作
Copper-Policy: Focus on the Representation for Robust Robot Manipulation
arXiv 2609.32779 · 2026-09-29智能体网络流量监控
Agentic Network Traffic Monitoring
arXiv 2609.32778 · 2026-09-29LLM智能体的行为特征研究
On the Behavioral Traits of LLM Agents
arXiv 2609.32776 · 2026-09-29基于Q-指数代理模型的鲁棒贝叶斯优化
Robust Bayesian Optimization with Q-Exponential Surrogates
arXiv 2609.32775 · 2026-09-29超越高斯假设：面向有效连接性的分布感知信道容量
Beyond Gaussian Assumptions: Distribution-Aware Channel Capacity for Effective Connectivity
arXiv 2609.32774 · 2026-09-29利用新闻衍生的货币政策信号预测日内美元/加元汇率
Forecasting Intraday USD/CAD Exchange Rate with News-Derived Monetary-Policy Signals
arXiv 2609.32773 · 2026-09-29可学习的随机化作为对抗自适应优化器的承诺
Learnable Randomization as Commitment Against Adaptive Optimizers
arXiv 2609.32772 · 2026-09-29通过自探针梯度进行持续学习
Continual Learning via Self-Probe Gradients
arXiv 2609.32771 · 2026-09-29C-HAT-Bench：超越全生成文本的中文AI文本检测基准
C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text
arXiv 2609.32770 · 2026-09-29你无法识破深度伪造？你的大脑和眼睛也不能：深度伪造利用认知参与和隐式视觉评估的神经生理学框架
You Can't Spot a Deepfake?And Neither Can Your Brain Nor Eyes: A Neurophysiological Framework for Deepfake Exploitation of Cognitive Engagement and Implicit Visual Evaluation
arXiv 2609.32769 · 2026-09-29无序随机图上的三体、二体与局域化
Trimers, pairs and localisation on disordered random graphs
arXiv 2609.32768 · 2026-09-29CLAP：带压力的闭环对齐实现精确吸取操作
CLAP: Closed-Loop Alignment with Pressure for Precise Suction Manipulation
arXiv 2609.32767 · 2026-09-29通过协议-目标-资源归约构建学习范式间的关系结构
Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductions
arXiv 2609.32766 · 2026-09-29快速均值回复随机波动率下的蒙特卡洛定价：多尺度极限 ${\epsilon\to 0}$
Monte Carlo pricing under fast mean-reverting stochastic volatility: the multi-scale limit ${ε\to 0}$
arXiv 2609.32765 · 2026-09-29AnchorMixGAN：云集成物联网网络中DDoS检测的锚定对齐生成式半监督方法
AnchorMixGAN: Anchor-Aligned Generative Semi-Supervision for DDoS Detection in Cloud-Integrated IoT Networks
arXiv 2609.32764 · 2026-09-29Mandela-Bench：多模态模型记住规范图像而非真正看见它们
Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them
arXiv 2609.32763 · 2026-09-29视觉模仿学习中视点泛化策略关键因素的实证研究
An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learning
arXiv 2609.32762 · 2026-09-29从前馈到流：统一重建与生成比想象中更简单
From Feed-Forward to Flow: Unifying Reconstruction and Generation Is Easier Than You Think
arXiv 2609.32761 · 2026-09-29通过溅射沉积相选择性生长水溶性铝酸锶用于自支撑氧化物薄膜
Phase-selective growth of water-soluble strontium aluminate via sputtering deposition for freestanding oxide membranes
arXiv 2609.32760 · 2026-09-29Extender：一种日志结构化的 Transformer
The Extender: A Log-Structured Transformer
arXiv 2609.32759 · 2026-09-29人格效应在语言模型中的泛化程度如何？
How Far Do Persona Effects Generalize in Language Models?
arXiv 2609.32758 · 2026-09-29读出并非恢复：在视觉-语言模型中解离坐标发射与视觉损坏修复
Readout is not Recovery: Dissociating Coordinate Emission from Visual-Corruption Repair in Vision-Language Models
arXiv 2609.32757 · 2026-09-29重用还是重新学习？地球观测基础模型的谱视角
Reuse or Relearn? A Spectral View of Earth Observation Foundation Models
arXiv 2609.32756 · 2026-09-29使 Euclid VIS 成像具备 AI 就绪性：用于形态学、异常检测和相似性搜索的可扩展流水线
Making Euclid VIS Imaging AI-Ready: A Scalable Pipeline for Morphology, Anomaly Detection, and Similarity Search
arXiv 2609.32753 · 2026-09-29向量丛的弱正性与弱平坦性
Weak positivity and weak flatness of vector bundles
arXiv 2609.32751 · 2026-09-29CUA-Sandbox：用于计算机使用代理强化学习的高效环境
CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning
arXiv 2609.32750 · 2026-09-29基于归一化响应相似性的回顾性蒸馏归因
Retrospective Distillation Attribution via Normalized Response Similarity
arXiv 2609.32749 · 2026-09-29全息探针膜金属中慢电流的非线性极点拓扑
Nonlinear pole topology of slow currents in holographic probe-brane metals
arXiv 2609.32748 · 2026-09-29四旋翼系统在网络攻击下的路径不变性及其理论保证
Path Invariance of a Quadrotor System under Cyber Attacks with Theoretical Guarantees
arXiv 2609.32747 · 2026-09-29自进化多智能体符号发现用于金融基本面分析
Self-Evolving Multi-Agent Symbolic Discovery for Financial Fundamental Analysis
arXiv 2609.32746 · 2026-09-29MORPH：基于神经可塑性启发的自适应拓扑的多机器人自组织任务分配
MORPH: Self-Organising Multi-Robot Task Allocation via Neuroplasticity-Inspired Adaptive Topology
arXiv 2609.32745 · 2026-09-29单点扩张的导出去环水平与有限维数
Derived Delooping Levels of One-Point Extensions and Finitistic Dimensions
arXiv 2609.32744 · 2026-09-29脑电图基础模型规模化基准测试：来自20,000次评估的经验教训
Benchmarking EEG Foundation Models at Scale: Lessons from 20,000 Evaluations
arXiv 2609.32743 · 2026-09-29LoCoVSR：用于视频超分辨率的局部上下文扩散后验采样
LoCoVSR: Local Context Diffusion Posterior Sampling for Video Super-Resolution
arXiv 2609.32742 · 2026-09-29预测主要AI相关半导体企业供应链风险的财务影响：一种异构图补丁Transformer方法
Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach
arXiv 2609.32741 · 2026-09-29聊天机器人互动并不总能产生元学习：来自三个国家的证据
Chatbot Engagement Does Not Always Beget Metalearning: Evidence from Three Countries
arXiv 2609.32739 · 2026-09-29排除Braess悖论并保持随时间流单调性的网络拓扑
Network Topology That Excludes Braess's Paradox and Maintains Monotonicity in Flows Over Time
arXiv 2609.32738 · 2026-09-29
