2026-09论文中文摘要
Batchelor-Kraichnan随机流中二维高斯聚合物的分块摩擦异质性对拉伸的重新分布
Blockwise friction heterogeneity redistributes stretching in a 2D Gaussian polymer under Batchelor-Kraichnan random flow
arXiv 2609.31707 · 2026-09-29找不到 Waldo：评估视觉语言模型对图像分辨率和细节水平的敏感性
Can't Find Waldo: Evaluating VLMs' Sensitivity to Image Resolution and Detail Level
arXiv 2609.31706 · 2026-09-29MDL校准的显著性增益对编码：用于子词标记化的复制感知自动停止
MDL-Calibrated Significance-Gain Pair Encoding: Replication-Aware Automatic Stopping for Subword Tokenization
arXiv 2609.31705 · 2026-09-29小心你信任的对象：LLM多智能体博弈中受污染通信下的协调动态
Be Careful Who You Trust: Coordination Dynamics under Corrupted Communication in LLM Multi-Agent Games
arXiv 2609.31704 · 2026-09-29DiffVQE2：一种用于声学回声和噪声控制的高效低延迟扩散模型
DiffVQE2: An Efficient Low-delay Diffusion Model for Acoustic Echo and Noise Control
arXiv 2609.31703 · 2026-09-29CLC-YOLO：一种用于实时泄漏感知乳腺超声病变分割的紧凑通道门控原型网络
CLC-YOLO: A Compact Channel-Gated Prototype Network for Real-Time Leakage-Aware Breast Ultrasound Lesion Segmentation
arXiv 2609.31702 · 2026-09-29基于混合优化策略的集成深度学习框架用于家蚕自动化健康检测与分析
Integrated Deep Learning Framework Designed on Hybrid Optimization Strategies for Automated Health Detection and Analysis in Silkworms
arXiv 2609.31701 · 2026-09-29现代化压缩域视频字幕生成器：SigLIP2与GPT-2替换的受控研究
Modernising the Compressed-Domain Video Captioner: A Controlled Study of SigLIP2 and GPT-2 Substitutions
arXiv 2609.31700 · 2026-09-29归一化还是条件化？无人机旋翼自噪声下机载关键词识别的噪声基底前端
Normalise or condition? Noise-floor front-ends for on-board keyword spotting under UAV rotor ego-noise
arXiv 2609.31699 · 2026-09-29低光条件下的视频字幕生成：高效的不确定性感知字幕校正
Video Captioning in Low-Light Conditions through Efficient Uncertainty-Aware Caption Correction
arXiv 2609.31697 · 2026-09-29推荐系统离线评估中的数据预处理：综述
Data Processing for Offline Evaluation in Recommender Systems: a Survey
arXiv 2609.31696 · 2026-09-29任意连续概率分布族的约束替代数据
Constrained surrogates for arbitrary families of continuous probability distributions
arXiv 2609.31695 · 2026-09-29RemTraceNet：不可见水印攻击的少样本取证检测
RemTraceNet: Few-Shot Forensic Detection of Invisible Watermark Attacks
arXiv 2609.31694 · 2026-09-29解耦与丢弃：通过重建灰度残差分解实现鲁棒的通用图像水印去除
Disentangle and Drop: Robust Universal Removal of Image Watermarks via Reconstructive Grayscale Residual Decomposition
arXiv 2609.31693 · 2026-09-29面向乳腺癌诊断的可解释深度学习架构感知鲁棒性评估
Architecture-aware Robustness Evaluation of Explainable Deep Learning for Breast Cancer Diagnosis
arXiv 2609.31692 · 2026-09-29平面平行集的空洞：一个积分贝蒂数界及其逐点失效
Holes in planar parallel sets: An integrated Betti-number bound and its pointwise failure
arXiv 2609.31691 · 2026-09-29适配视觉-语言模型用于工业目标检测中的人类可读可解释人工智能
Adapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection
arXiv 2609.31690 · 2026-09-29有限缺陷刚性与二维球面上的最小球面4-设计
Finite-Defect Rigidity and the Minimum Spherical 4-Design on the Two-Sphere
arXiv 2609.31689 · 2026-09-29使用CIVL验证PETSc：基于LLM生成的ACSL契约与确定性驱动程序生成
Verification of PETSc with CIVL using LLM-generated ACSL contracts and deterministic driver generation
arXiv 2609.31687 · 2026-09-29美国西海岸枢纽国内航空的三维排放制图与社会成本估算
3-D Emissions Mapping and Social Cost Estimation for US Domestic Aviation at West Coast Hubs
arXiv 2609.31686 · 2026-09-29FFN压缩会改变下游什么？扩散语言模型中的同状态因果恢复
What does FFN compression change downstream? Same-state causal restoration in diffusion language models
arXiv 2609.31685 · 2026-09-29时间拉锯战：通过轨迹方差可视化和检测扩散模型中的RAG冲突
The Temporal Tug-of-War: Visualizing and Detecting RAG Conflicts in Diffusion Models via Trajectory Variance
arXiv 2609.31684 · 2026-09-29自主研究项目管理作为智能体技能：精确谱空间回归的案例研究
Autonomous Research Project Management as an Agent Skill: A Case Study in Exact Spectral Spatial Regression
arXiv 2609.31683 · 2026-09-29Devanagari手写字符识别使用TrOCR：一种基于Transformer的模型与实时Web部署
Devanagari Handwritten Character Recognition Using TrOCR: A Transformer-Based Model with Real-Time Web Deployment
arXiv 2609.31681 · 2026-09-29联合嵌入预测架构预训练是否有助于时间序列预测？
Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?
arXiv 2609.31680 · 2026-09-29迈向AI辅助家禽球虫病诊断：评估Gemini和BiomedParse在艾美耳球虫显微镜图像上的表现
Toward AI-Assisted Poultry Coccidiosis Diagnosis: Evaluating Gemini and BiomedParse on Eimeria Microscopy Images
arXiv 2609.31679 · 2026-09-29当关键词下降但分类器保持：KV缓存压缩下的软拒绝
When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression
arXiv 2609.31678 · 2026-09-29基于SoF数据集的部分人脸识别中CNN骨干网络的比较迁移学习研究
A Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset
arXiv 2609.31677 · 2026-09-29AI支持的基于证据的学习在公众演讲技能培养中的评估
An Evaluation of AI-Supported Evidence-Based Learning for Public Speaking Skill Development
arXiv 2609.31676 · 2026-09-29主动因果发现基准：评估预算干预下的LLM智能体
Active Causal Discovery Benchmark: Evaluating LLM Agents Under Budgeted Interventions
arXiv 2609.31675 · 2026-09-29平衡汉明图与网格的精确多数C-着色
Exact majority C-colourings of balanced Hamming graphs and grids
arXiv 2609.31674 · 2026-09-29OneVoice：智能体语音流水线的中间表示
OneVoice: An Intermediate Representation for Agentic Speech Pipelines
arXiv 2609.31673 · 2026-09-29从三流体交界到杨氏定律：本构与刚性支撑极限下的润湿
From a three-fluid junction to Young's law: Constitutive and rigid-support limits of wetting
arXiv 2609.31672 · 2026-09-29用于基于事件的行人穿越检测的无监督脉冲特征学习：在无标注训练数据下接近监督精度
Unsupervised spiking feature learning for event-based pedestrian crossing detection: approaching supervised accuracy without labelled training data
arXiv 2609.31671 · 2026-09-29单步即最优：无条件整流流是 Noise2Noise 去噪器，多步积分确有损害——低剂量 CT 上的基准与基于任务的检测性研究
One-Step Is Optimal: Unconditional Rectified Flows are Noise2Noise Denoisers, and Multi-Step Integration Provably Hurts---A Benchmark and Task-Based Detectability Study on Low-Dose CT
arXiv 2609.31670 · 2026-09-29NanoForecast v0.5：通过训练流程优化实现具有竞争力的时间序列预测
NanoForecast v0.5: Competitive Time Series Forecasting Through Training Pipeline Optimization
arXiv 2609.31669 · 2026-09-29查询对齐的视频帧选择用于长视频理解
Query-aligned video frame selection for long video understanding
arXiv 2609.31668 · 2026-09-29超越图结构：一种自适应元学习器融合可解释性、天气与动态信息用于稳健的公交ETA预测
Beyond the Graph: An Adaptive Meta-Learner Fuses Explainability, Weather, and Dynamics for Robust Bus ETA Prediction
arXiv 2609.31667 · 2026-09-29基于共享表示和领域特定头的IMU数字笔年龄自适应手写重建
Age-Adaptive Handwriting Reconstruction from an IMU-Based Digital Pen through Shared Representations and Domain-Specific Heads
arXiv 2609.31666 · 2026-09-29什么驱动方言越狱？表面形式、文化框架与策略库的消融研究
What Drives Dialectal Jailbreaks? An Ablation of Surface Form, Cultural Framing, and Strategy Banks
arXiv 2609.31664 · 2026-09-29LLM引导的基于本体的非结构化文本知识图谱构建
LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text
arXiv 2609.31663 · 2026-09-29稳定学习：累积相对点边际分数用于人脸图像质量评估
Learning Steadily: Accumulating Relative Point Margin Scores for Face Image Quality Assessment
arXiv 2609.31662 · 2026-09-29ForensicZoom：基于多模态大语言模型的自适应视觉检查用于工业级人脸伪造检测
ForensicZoom: Adaptive Visual Inspection with Multimodal LLMs for Industrial-Grade Face Forgery Detection
arXiv 2609.31661 · 2026-09-29解析器、分块与嵌入在印度政府监管文档检索增强生成中的交互作用
Parser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents
arXiv 2609.31660 · 2026-09-29波形协变量偏移下磁芯损耗预测的跨材料支持迁移
Cross-Material Support Transfer for Core-Loss Prediction Under Waveform Covariate Shift
arXiv 2609.31659 · 2026-09-29跨数据集迁移与未知类别检测：不平衡SAR舰船分类
Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification
arXiv 2609.31658 · 2026-09-29通过目标过采样增强基础模型以应对不平衡SAR船舶分类
Enhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling
arXiv 2609.31657 · 2026-09-29从相变到系统性失效：GNN鲁棒性的解耦分析框架
From Phase Transition to Systemic Failure: A Decoupled Analytics Framework for GNN Robustness
arXiv 2609.31656 · 2026-09-29一次评估，任意工作点：基于超网络摊销MeanFlow的3D MRI重建
One Evaluation, Any Operating Point: Hypernetwork-Amortized MeanFlow for 3D MRI Reconstruction
arXiv 2609.31655 · 2026-09-29消费者投诉评估中的分布情感建模与异常检测
Distributional sentiment modeling and anomaly detection for consumer complaint assessment
arXiv 2609.31653 · 2026-09-29
