2026-09论文中文摘要
一个不余生成的适当 dg 代数
A proper dg algebra which does not cogenerate
arXiv 2609.34193 · 2026-09-29RidgeRank：通过分数融合与浅层线性读出实现高效的视觉文档重排序
RidgeRank: Efficient Visual Document Reranking via Score Fusion and a Shallow Linear Readout
arXiv 2609.34192 · 2026-09-29基数分层交互分解：用于交易篮子数据中可解释的成对与高阶结构
Cardinality-Stratified Interaction Decomposition for Interpretable Pairwise and Higher-Order Structure in Transactional Basket Data
arXiv 2609.34191 · 2026-09-29MotionSpaceFlow：直接运动空间中的表示感知流匹配
MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Space
arXiv 2609.34190 · 2026-09-29类银河系星系的形态统计
Morphological Statistic of Milky Way-like Galaxies
arXiv 2609.34189 · 2026-09-29AlphaPareto：基于LLM引导的多目标强化学习的公式化Alpha发现
AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning
arXiv 2609.34188 · 2026-09-29整合生化模型与实验数据的交互式模拟器
An interactive simulator for integrating biochemical models with experimental data
arXiv 2609.34186 · 2026-09-29EntroPack：任意比特率下的快速准确熵编码权重压缩
EntroPack: Fast and Accurate Entropy-Coded Weight Compression at Arbitrary Bitrates
arXiv 2609.34185 · 2026-09-29CASS：面向模型合并的贡献感知结构化稀疏性
CASS: Contribution-Aware Structured Sparsity for Model Merging
arXiv 2609.34184 · 2026-09-29CRF损失是弱监督分割中网络应如何学习边界的方式
CRF Loss is How Networks Should Learn Boundaries in Weakly Supervised Segmentation
arXiv 2609.34183 · 2026-09-29面向文本介导视频异常检测的决策读出：Jev与Qwen的探索性评估
Decision Readouts for Text-Mediated Video Anomaly Detection: An Exploratory Evaluation of Jev and Qwen
arXiv 2609.34180 · 2026-09-29RAGWarrant：在质量、成本、延迟和风险约束下的RAG策略推广的保留证据治理
RAGWarrant: Evidence-Preserving Governance for RAG Policy Promotion Under Quality, Cost, Latency, and Risk Constraints
arXiv 2609.34179 · 2026-09-29AGILE-GS：面向主动三维高斯泼溅的锚点引导快速下一最佳视角选择
AGILE-GS: Anchor-Guided Fast Next-Best-View Selection for Active 3D Gaussian Splatting
arXiv 2609.34176 · 2026-09-29FailPatch：视觉-语言-动作模型的失败残差修补
FailPatch: Failure Residual Patching for Vision-Language-Action Models
arXiv 2609.34175 · 2026-09-29控制系统的一种弱对称性概念
A Weak Notion of Symmetry for Control Systems
arXiv 2609.34173 · 2026-09-29GPARA：用于接地扩散先验的图后验对齐精化与主动采集
GPARA: Graph-Posterior-Aligned Refinement and Active Acquisition for Grounding Diffusion Priors
arXiv 2609.34172 · 2026-09-29驱动-耗散临界性下的单片集成光子神经网络
Monolithically integrated photonic neural network at driven-dissipative criticality
arXiv 2609.34171 · 2026-09-29RAVEL：面向基于流的视觉-语言-动作模型的异步滚动推理
RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models
arXiv 2609.34170 · 2026-09-29从词频到语境：资产定价中的主题模型
From Word Counts to Context: Topic Models for Asset Pricing
arXiv 2609.34169 · 2026-09-29二维稳态不可压缩流的几何与函数混合
Geometric and functional mixing by 2D stationary incompressible flows
arXiv 2609.34168 · 2026-09-29隐藏激活并不足够 I：知识矩阵作为更高表示
Hidden Activations are not Enough I: Knowledge Matrices as Higher Representations
arXiv 2609.34166 · 2026-09-29阿基米德 Asai $L$-函数的例外极点
Exceptional poles of archimedean Asai $L$-functions
arXiv 2609.34165 · 2026-09-29面向往返视觉语言导航的可靠性感知稀疏路径记忆
Reliability-Aware Sparse Route Memory for Round-Trip Vision-Language Navigation
arXiv 2609.34163 · 2026-09-29SlideDP：跨多GPU扩展宿主机驻留的大语言模型微调
SlideDP: Scaling Host-Resident LLM Fine-Tuning Across Multiple GPUs
arXiv 2609.34162 · 2026-09-29GT-PSSM：用于多元时间序列异常检测中随机动力学建模与依赖学习的统一概率框架
GT-PSSM: Unified Probabilistic Framework for Stochastic Dynamics Modeling and Dependency Learning in Multivariate Time Series Anomaly Detection
arXiv 2609.34161 · 2026-09-29RoutePrism：追踪智能体记忆中构建顺序的影响
RoutePrism: Tracing Construction Order Effects in Agent Memory
arXiv 2609.34160 · 2026-09-29WorldGraph：图原生世界建模
WorldGraph: Graph-Native World Modeling
arXiv 2609.34159 · 2026-09-29迈向大语言模型信念稳定性的分级度量
Toward a Graded Measure of Belief Stability in Large Language Models
arXiv 2609.34158 · 2026-09-29TableSeek：异构表格语料库上保持结构的智能体证据搜寻
TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corpora
arXiv 2609.34157 · 2026-09-29迁移校准预测增强推断
Transfer Calibrated Prediction Powered Inference
arXiv 2609.34156 · 2026-09-29对《银河系中心过剩的暗物质形态：银河系模拟中的费米-LAT》一文的评论
Comment on "Fermi-LAT Galactic Center Excess Morphology of Dark Matter in Simulations of the Milky Way Galaxy"
arXiv 2609.34155 · 2026-09-29极值Ricci-pinched $G_2$-结构的性质与扰动
Properties and Perturbations of Extremally Ricci-Pinched $G_2$-Structures
arXiv 2609.34154 · 2026-09-29SPINET：层化蛋白质逆折叠网络
SPINET: Sheaf Protein Inverse Folding Network
arXiv 2609.34153 · 2026-09-29基于预训练语言模型的近亲印欧语系语言距离定量测量：以北日耳曼语支为例
Quantitative Measurement of Language Distance among Closely Related Indo-European Languages Using Pretrained Language Models: A Case Study on the North Germanic Branch
arXiv 2609.34152 · 2026-09-29自进化智能体：基于似然引导的工具空间优化
Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization
arXiv 2609.34151 · 2026-09-29PEGASUS（昴星团望远镜PFS发射线星系巡天）：II. 高等值宽度窄带发射线天体中的贫金属活动星系核
PEGASUS (Pfs Emission-line GAlaxy SUrvey with Subaru): II. Metal Poor AGNs in High Equivalent-Width Narrow-Band Emitters
arXiv 2609.34150 · 2026-09-29功能手型先验用于第一人称视角单目视频的3D手部姿态估计与动作识别
Functional Hand Type Prior for 3D Hand Pose Estimation and Action Recognition from Egocentric View Monocular Videos
arXiv 2609.34149 · 2026-09-29视觉-语言模型中空间推理的几何编码
Geometric Encoding for Spatial Reasoning in Vision-Language Models
arXiv 2609.34148 · 2026-09-29SPEAR-Gen：面向统一语音表示的生成感知预训练
SPEAR-Gen: Generation-Aware Pre-training for Unified Speech Representations
arXiv 2609.34147 · 2026-09-29ExpertoRhythm：面向单通道PPG波形重建与无袖带血压估计的形态感知学习
ExpertoRhythm: Morphology-Aware Learning for Waveform Reconstruction and Cuffless Blood Pressure Estimation from Single-Channel PPG
arXiv 2609.34146 · 2026-09-29超越检索相关性：面向视觉-语言驾驶的场景锚定风险蕴含
Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving
arXiv 2609.34145 · 2026-09-29CAST：交互式世界模型的重建耦合加速
CAST: Reconstruction-Coupled Acceleration of Interactive World Models
arXiv 2609.34144 · 2026-09-29超越几何：面向3D逻辑异常检测的基准测试与一致性推理
Beyond Geometry: Benchmarking and Consistency Reasoning for 3D Logical Anomaly Detection
arXiv 2609.34143 · 2026-09-29基于解析与卷积神经网络的运动矢量传播用于高效视频目标检测
Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection
arXiv 2609.34142 · 2026-09-29标量曲率下界与测度收敛
Scalar Curvature Lower Bounds and Convergence in Measure
arXiv 2609.34141 · 2026-09-29基于情景系统负荷预测的长期运行规划
Long-Term Operational Planning Using Scenario-Based System Load Forecasting
arXiv 2609.34140 · 2026-09-29相同任务，不同应用：移动GUI智能体为何难以泛化？
Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize?
arXiv 2609.34139 · 2026-09-29印度语言词语相似度数据集：标注与基线系统
Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems
arXiv 2609.34138 · 2026-09-29鱼与熊掌不可兼得：概念纠缠限制了扩散模型的去学习能力
You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
arXiv 2609.34137 · 2026-09-29Waggle：为自组织LLM智能体群学习一个匿名局部法则
Waggle: Learning One Anonymous Local Law for Self-Organizing LLM Swarms
arXiv 2609.34136 · 2026-09-29
