2026-09论文中文摘要
先校正后预测：用于时间序列预测的观测器状态空间模型
Correct then Forecast: Observer State-Space Models for Time Series Forecasting
arXiv 2609.33566 · 2026-09-29Dr. Free：自进化搜索智能体无需难度奖励
Dr. Free: You Don't Need Difficulty Rewards for Self-Evolving Search Agents
arXiv 2609.33565 · 2026-09-29Fibonacci-Lucas zeta 和的消去轮廓
Cancellation profiles of Fibonacci-Lucas zeta sums
arXiv 2609.33564 · 2026-09-29OOD泛化作为分岔问题
OOD Generalization as a Bifurcation Problem
arXiv 2609.33562 · 2026-09-29GraphSelect：多模态图推断中的预算表示选择
GraphSelect for Budgeted Representation Selection in Multimodal Graph Inference
arXiv 2609.33561 · 2026-09-29一般非退化卷积 Calderón--Zygmund 算子的 Sharp 矩阵 $\mathcal A_p$ 下界
Sharp Matrix $\mathcal A_p$ lower bounds for general non-degenerate convolution Calderón--Zygmund operators
arXiv 2609.33560 · 2026-09-29直到微调前都很好：重复解决方案使推理变得脆弱
Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile
arXiv 2609.33559 · 2026-09-29非齐次随机圆盘型康托尔集的Favard长度
Favard length of non-homogeneous random disc-like Cantor sets
arXiv 2609.33557 · 2026-09-29当群体具有吸引力：合作与个体及群体模仿规则的共同进化动力学
When groups attract: coevolutionary dynamics of cooperation and individual- and group-based imitating rules
arXiv 2609.33556 · 2026-09-29三维至六维加权 Neumann 与 Steklov 特征值的等周界
Isoperimetric bounds for the weighted Neumann and Steklov eigenvalues in dimensions three through six
arXiv 2609.33555 · 2026-09-29一种用于低码率一阶环境立体声的高效参数化编解码器
An Efficient Parametric Codec for Low-Bitrate First-Order Ambisonics
arXiv 2609.33554 · 2026-09-29构网型E-STATCOM用于大规模数据中心稳定集成：建模与控制
Grid-Forming E-STATCOMs for Stable Integration of Large-Scale Data Centers: Modeling and Control
arXiv 2609.33553 · 2026-09-29FoLD：面向灵巧关节物体操作的力量知情学习
FoLD: Force-Informed Learning for Dexterous Articulated Object Manipulation
arXiv 2609.33551 · 2026-09-29默认稀疏性：高斯过程回归中ARD用于变量选择的理论与实践
Sparsity by Default: The Theory and Practice of ARD in Gaussian Process Regression for Variable Selection
arXiv 2609.33550 · 2026-09-29校准的高斯过程变量选择中的导数过程灵敏度
Calibrated Derivative-Process Sensitivity for Gaussian-Process Variable Selection
arXiv 2609.33549 · 2026-09-29TerMeZO：面向边缘BitNet模型微调的三元稀疏零阶优化
TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge
arXiv 2609.33548 · 2026-09-29Steer2Grasp：推理时具身感知引导用于多样化物理可行抓取扩散
Steer2Grasp: Inference-Time Embodiment-Aware Steering for Diverse Physically Feasible Grasp Diffusion
arXiv 2609.33546 · 2026-09-29碳化硅膜中通过异相界面工程调控缺陷-声子相互作用
Engineering Defect-Phonon Interactions Through Heterophase-Interfaces in Silicon Carbide Membranes
arXiv 2609.33545 · 2026-09-29边缘网络中联邦学习工作流管理的自适应客户端聚类与协调
Adaptive Client Clustering and Coordination for Federated Learning Workflow Management in Edge Networks
arXiv 2609.33544 · 2026-09-29OSCC：不完美信息学习中梯度噪声控制的认证观测安全耦合优化
OSCC: Certified Observation-Safe Coupling Optimization for Gradient-Noise Control in Imperfect-Information Learning
arXiv 2609.33543 · 2026-09-29多粒子 Oja 流的分析框架
An Analytical Framework for a Multi-Particle Oja Flow
arXiv 2609.33541 · 2026-09-29单纯形上的推理：几何不动点模型
Reasoning on the Simplex: Geometric Fixed-Point Models
arXiv 2609.33540 · 2026-09-29面向安全WLAN感知的向后兼容基于标签的物理层认证
Backward-Compatible Tag-Based PHY Authentication for Secure WLAN Sensing
arXiv 2609.33539 · 2026-09-29Jev 在语音神经假体重打分中匹敌 7B 语言模型
Jev Matches 7B Language Models for Speech-Neuroprosthesis Rescoring
arXiv 2609.33538 · 2026-09-29关于二阶实局部系的非阿贝尔Noether-Lefschetz轨迹的代数性
On the algebraicity of non-abelian Noether-Lefschetz loci of rank-two real local systems
arXiv 2609.33537 · 2026-09-29执行是否需要目标KV保真度？一种用于LLM服务的混合保真度KV运行时
Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving
arXiv 2609.33536 · 2026-09-29近乎群可分离的选举
Nearly Group-Separable Elections
arXiv 2609.33535 · 2026-09-29ManiEdit：从流形视角对语言模型进行顺序非结构化知识编辑
ManiEdit: Sequential Unstructured Knowledge Editing for Language Models from a Manifold Perspective
arXiv 2609.33534 · 2026-09-29Transformer算子网络的神经缩放定律
Neural Scaling Laws of Transformer Operator Network
arXiv 2609.33533 · 2026-09-29数字从何而来：基于溯源入侵检测中的评估审计
Where the Numbers Come From: Auditing Evaluation in Provenance-Based Intrusion Detection
arXiv 2609.33532 · 2026-09-29广义混合序列重数
Generalized mixed sequence multiplicity
arXiv 2609.33531 · 2026-09-29E-CONAN（蕴含、矛盾与中立）诊断数据集：探究阿拉伯语自然语言理解中的语言现象
E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding
arXiv 2609.33530 · 2026-09-29拉马努金初等连分数的初等处理
An elementary treatment of Ramanujan's elementary continued fractions
arXiv 2609.33529 · 2026-09-29基于前期气象条件的道路结冰预警：无一致临界减速现象
Early warning of road icing from antecedent meteorological conditions without consistent critical slowing down
arXiv 2609.33528 · 2026-09-29发现神经网络参数空间中的对称性
Discovering Symmetries in Neural Network Parameter Spaces
arXiv 2609.33527 · 2026-09-29显式分形图：素数阶 Paley 图及其他 Cayley 图
Explicit Fractalizers: Prime-Order Paley Graphs and other Cayley Graphs
arXiv 2609.33526 · 2026-09-29AI生成合成人物中数字内容使用情境的潜在类别分析
Latent Class Analysis of Digital Content Use Contexts in AI-Generated Synthetic Personas
arXiv 2609.33525 · 2026-09-29EverMine：剖析长周期Alpha研究中研究能力的自我进化
EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research
arXiv 2609.33524 · 2026-09-29In-Token Learning：基于扩散Transformer的高保真图像恢复
In-Token Learning for High-Fidelity Image Restoration via Diffusion Transformers
arXiv 2609.33523 · 2026-09-29AI驱动的协作装配线检测：系统集成与部署挑战
AI-Driven Collaborative Assembly Line Inspection: System Integration and Deployment Challenges
arXiv 2609.33522 · 2026-09-29LLM4Trust：探索大型语言模型在信任评估中的能力
LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation
arXiv 2609.33521 · 2026-09-29解剖结构分层多实例学习用于胸部X光片弱监督胸科疾病检测
Anatomy-Structured Hierarchical MIL for Weakly-Supervised Thoracic Disease Detection in Chest X-rays
arXiv 2609.33520 · 2026-09-29度量图上的光滑各向同性协方差函数：基于多调和电阻距离
Smooth Isotropic Covariance Functions on Metric Graphs via Polyharmonic Resistance Distances
arXiv 2609.33519 · 2026-09-29SceneScaffold：面向统一三维场景理解的活动场景状态构建
SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding
arXiv 2609.33518 · 2026-09-29TRACE：演化多智能体系统中的记忆有效性治理
TRACE: Governing Memory Validity in Evolving Multi-Agent Systems
arXiv 2609.33517 · 2026-09-29PPG-LM：具有多层级临床对齐的光电容积描记-语言模型
PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment
arXiv 2609.33516 · 2026-09-29SLP-ProbHard：通过结构潜在参数化的概率硬约束学习
SLP-ProbHard: Probabilistic Hard-Constrained Learning via Structural Latent Parameterization
arXiv 2609.33515 · 2026-09-29未来轻子对撞机暗物质搜寻的Mono-Z信号及宇宙学解释
Mono-Z signal for dark matter searches at future lepton colliders and cosmological interpretation
arXiv 2609.33514 · 2026-09-29近天底航空感知的打印约束对抗贴花：实测油墨色域、嵌套真实感约束与物理世界界限
Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Bound
arXiv 2609.33513 · 2026-09-29流匹配模型中用于物理一致性的源锚定
Source Anchoring for Physical Consistency in Flow Matching Models
arXiv 2609.33510 · 2026-09-29
