2026-09论文中文摘要
超越分类准确率：量化加密暗网服务中的指纹复杂度
Beyond Classification Accuracy: Quantifying Fingerprint Complexity in Encrypted Darknet Services
arXiv 2609.26096 · 2026-09-23FusionMMT：面向核聚变的统一多模态多任务学习框架
FusionMMT: A Unified Multimodal and Multitask Learning Framework for Nuclear Fusion
arXiv 2609.26095 · 2026-09-23CoEvo：单一模型的预言机接地自进化用于多步因果推理
CoEvo: Oracle-Grounded Self-Evolution of a Single Model for Multi-Step Causal Reasoning
arXiv 2609.26094 · 2026-09-23RECAP：用于检测视觉语言模型中空间关系幻觉的关系证据校准
RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models
arXiv 2609.26093 · 2026-09-23一对一匹配，图学习：面向目标检测的带反向共享的一对图查询协作
Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection
arXiv 2609.26092 · 2026-09-23从双线性到线性：基于低维参数化的差分隐私联邦LoRA
From Bilinear to Linear: Differentially Private Federated LoRA via Low-Dimensional Parameterization
arXiv 2609.26091 · 2026-09-23SpecialEduBench：面向自闭症儿童语言干预中知识、技能与态度的视觉语言模型基准测试
SpecialEduBench: Benchmarking Vision-Language Models on Knowledge, Skill, and Attitude in Language Intervention for Autistic Children
arXiv 2609.26090 · 2026-09-23具有常全纯截面曲率的平衡Bismut挠率平行流形
Balanced Bismut torsion-parallel manifold with constant holomorphic sectional curvature
arXiv 2609.26089 · 2026-09-23BDSLI：一种用于孟加拉手语翻译的混合CNN-Transformer模型
BDSLI: A hybrid CNN-Transformer model for Bengali Sign Language interpretation
arXiv 2609.26088 · 2026-09-23架构师、对抗者与评审者：大规模标准对齐评估题目的闭环生成
The Architect, the Adversary, and the Judge: Closed-Loop Generation of Standards-Aligned Assessment Items at Scale
arXiv 2609.26087 · 2026-09-23CoVeR：智能体检索中验证器调用的覆盖率路由
CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrieval
arXiv 2609.26086 · 2026-09-23声学椭圆：基于频率扫描的仿生全向回声定位在协作多智能体系统中的应用
Acoustic Ellipses: Bio-Inspired Omnidirectional Echolocation in Cooperative Multi-Agent Systems using Frequency Sweeps
arXiv 2609.26085 · 2026-09-23视觉语言模型作为自主无人机导航的副驾驶：退化环境中的延迟与可靠性分析
Vision-Language Models as copilots for Autonomous UAV Navigation: Analysis of Latency and Reliability in Degraded Environments
arXiv 2609.26084 · 2026-09-23共享环境中双移动协作机器人的情境感知运动框架
Situation Aware Locomotion for Dual Mobile Cobots in Shared Environments
arXiv 2609.26083 · 2026-09-23光滑射影环面簇的Chow-Witt环的一个扇算法
A Fan Algorithm for Chow-Witt Rings of Smooth Projective Toric Varieties
arXiv 2609.26082 · 2026-09-23间隔下降坐标用于跨预算鲁棒性评估
Margin-Drop Coordinates for Cross-Budget Robustness Evaluation
arXiv 2609.26081 · 2026-09-23舰队即模型：利用Fusion-MoA Pioneer R1工程化集体智能
The Fleet Is the Model: Engineering Collective Intelligence with Fusion-MoA Pioneer R1
arXiv 2609.26080 · 2026-09-23学习关联：MAC地址随机化下BLE设备的自动重识别
Learning to Link: Automatic Re-identification of BLE Devices Under MAC Address Randomisation
arXiv 2609.26079 · 2026-09-23ToW3D：基于GAN的交互式点驱动网格编辑中的一致性感知方法
ToW3D: Consistency-aware Interactive Point-based Mesh Editing on GANs
arXiv 2609.26078 · 2026-09-23fp8 中的快速矩阵乘法：认证系数优化与实测误差
Fast Matrix Multiplication in fp8: Certified Coefficient Optimization and Measured Error
arXiv 2609.26077 · 2026-09-23面向隐私感知多智能体LLM工作流的选择不变通信编译器
Selection-Invariant Communication Compilers for Privacy-Aware Multi-Agent LLM Workflows
arXiv 2609.26076 · 2026-09-23Troesch方程与电荷分离
Troesch's equation with charge separation
arXiv 2609.26075 · 2026-09-23二维次二次增长变分积分驻点的Bernstein型结果
Bernstein type results for stationary points of variational integrals with subquadratic growth in two dimensions
arXiv 2609.26074 · 2026-09-23细胞通信级别的病理基础模型可解释性：基于微环境图蒸馏
Cellular-Communication-Level Interpretability for Pathology Foundation Models via Graph Distillation on Microenvironment
arXiv 2609.26073 · 2026-09-23策略支撑的选择性再生：应对智能体间通信污染
Policy-Backed Selective Regeneration under Tainted Inter-Agent Communication
arXiv 2609.26072 · 2026-09-23StrataVLA：面向视觉-语言-动作模型的分层高效3D几何基础
StrataVLA: Hierarchical and Efficient 3D Geometric Grounding for Vision-Language-Action Models
arXiv 2609.26071 · 2026-09-23从ECR等离子体源膨胀的氢等离子体流动动力学的实验与理论研究
Experimental and Theoretical Study of Flow Dynamics of Expanding Hydrogen Plasma from an ECR Plasma Source
arXiv 2609.26070 · 2026-09-23RankCert：模拟学习者何时可以安全选择AI导师？结构不确定性下的鲁棒决策认证
RankCert: When Can Simulated Learners Safely Select an AI Tutor? Robust Decision Certification Under Structural Uncertainty
arXiv 2609.26069 · 2026-09-23多层网络可行性几何上的可微策略传输
Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry
arXiv 2609.26068 · 2026-09-23FuncCode：在函数空间中压缩 Kolmogorov--Arnold 网络并采用硬件感知量化
FuncCode: Compressing Kolmogorov--Arnold Networks in Function Space with Hardware-Aware Quantization
arXiv 2609.26067 · 2026-09-23切换网络上分布式观测器的稳定性：耦合可交换的情形
On stability of a distributed observer over switching networks: The case of commutative coupling
arXiv 2609.26065 · 2026-09-23SPEANet：用于参数高效遥感目标检测的结构先验增强注意力网络
SPEANet: Structural Prior Enhanced Attention Network for Parameter-Efficient Remote Sensing Object Detection
arXiv 2609.26064 · 2026-09-23面向自适应联邦图聚类：一种全局社区感知的对比学习方法
Towards Adaptive Federated Graph Clustering: A Global Community-aware Contrastive Learning-based Approach
arXiv 2609.26063 · 2026-09-23本地与移民劳动力之间的替代弹性：一项元分析
The Elasticity of Substitution between Native and Immigrant Labor: A Meta-Analysis
arXiv 2609.26062 · 2026-09-23ChainUQ：面向大语言模型的推理一致性感知不确定性量化
ChainUQ: Reasoning Consistency-Aware Uncertainty Quantification for Large Language Models
arXiv 2609.26060 · 2026-09-23对抗性行动方案生成：用于COA匹配与COA生成的博弈论多智能体算法
Adversarial Course-of-Action Generation: Game-Theoretic Multi-Agent Algorithms for COA matching & COA generation
arXiv 2609.26059 · 2026-09-23观察生成式人工智能支持下的系统综述实施：来自软件工程研究生课程的经验报告
Observing the Conduct of Systematic Reviews with Generative AI Support: An Experience Report from a Graduate Software Engineering Course
arXiv 2609.26057 · 2026-09-23CricRAG：用于个性化板球教练的检索增强视觉语言模型
CricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching
arXiv 2609.26056 · 2026-09-23非退化全次数II型约化Ito多项式的随机实现
Stochastic realisers of non-degenerate full-degree Type II reduced Ito polynomials
arXiv 2609.26055 · 2026-09-23开源语音情感识别在自然场景中文脊柱门诊咨询中的基准测试：一项初步验证研究
Benchmarking Open-Source Speech Emotion Recognition in Naturalistic Mandarin Spine Clinic Consultations: A Pilot Validation Study
arXiv 2609.26054 · 2026-09-23智能交通网络的可观测性与冗余性研究
On the Observability and Redundancy of Intelligent Transportation Networks
arXiv 2609.26053 · 2026-09-23优化dLLMs中的去噪轨迹：一种轻量级进化启发式方法
Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach
arXiv 2609.26052 · 2026-09-23迈向意图感知的人机团队协作：面向搜索与救援任务的平台
Towards Intent-Aware Human-Robot Teaming: A Platform for Search-and-Rescue Operations
arXiv 2609.26051 · 2026-09-23关于OpenAI整立方体界
On the OpenAI whole-cube bound
arXiv 2609.26050 · 2026-09-23预紧阿贝尔群的可分商群的三个问题
Three Problems on Separable Quotients of Precompact Abelian Groups
arXiv 2609.26049 · 2026-09-23FIRE：面向可靠语言模型智能体的失败知情运行时工程
FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents
arXiv 2609.26048 · 2026-09-23可识别图像语言：通过通信复杂度将UREC与coUREC分离
Recognizable Picture Languages: Separating UREC from coUREC via Communication Complexity
arXiv 2609.26047 · 2026-09-23随机树中非正常边数量的极限分布
On the limiting distribution of the number of improper edges for random trees
arXiv 2609.26045 · 2026-09-23固定奇最大度的非正则图的极值谱半径
Extremal spectral radius of nonregular graphs with a fixed odd maximum degree
arXiv 2609.26044 · 2026-09-23表面-体态杂化增强GaAs(110)中的贝里曲率偶极子
Surface-bulk hybridization enhances the Berry curvature dipole in GaAs(110)
arXiv 2609.26043 · 2026-09-23
