2026-10论文中文摘要
通过循环原生注意力残差扩展至数万次测试时迭代
Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
arXiv 2610.11570 · 2026-10-09平面内两组正交曲线网的控制问题
On a control problem for two orthogonal nets of curves in the plane
arXiv 2610.11569 · 2026-10-09窄P_c态的选定开粲衰变：夸克交换预言与π介子交换敏感性
Selected open-charm decays of the narrow \(P_c\) states: Quark-interchange predictions and pion-exchange sensitivity
arXiv 2610.11568 · 2026-10-09Sera：用于可靠且可解释的电池健康预测的语义表示聚合
Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting
arXiv 2610.11567 · 2026-10-09基于结构化工具的增量开放式深度研究
Incremental Open-Ended Deep Research with Structured Harness
arXiv 2610.11566 · 2026-10-09临界上同调中特化映射的单射性
Injectivity of specialization maps in critical cohomology
arXiv 2610.11565 · 2026-10-09二维点涡系统的边界控制
Boundary Control of Two-dimensional Point-Vortex Systems
arXiv 2610.11564 · 2026-10-09Grant：支持多属性范围过滤的近似最近邻搜索框架
Grant: A Framework for Approximate Nearest Neighbor Search with Multi-Attribute Range Filters
arXiv 2610.11563 · 2026-10-09动力学平均场理论研究局域4f²电子体系中的多极涨落：应用于PrCdNi₄
Multipolar fluctuations in localized $4f^2$-electron systems from dynamical mean-field theory: application to $\mathrm{PrCdNi}_4$
arXiv 2610.11562 · 2026-10-09Workerville：构建组织行为视角下的智能体安全研究
Workerville: Towards an Organizational Behavior Account of Agent Safety
arXiv 2610.11561 · 2026-10-09用于并行磁共振成像重建的Hankel子空间自监督学习
Hankel Subspace Self-Supervised Learning for Parallel MRI Reconstruction
arXiv 2610.11560 · 2026-10-09SWE-Journey：通过长周期多轮交互实现代码助手更真实的评估
SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction
arXiv 2610.11559 · 2026-10-09面向高效信道状态信息反馈的基于模型的深度学习与秩一感知
Model-Driven Deep Learning with Rank-One Sensing for Efficient CSI Feedback
arXiv 2610.11558 · 2026-10-09打破交通流中的行为一致性：最优协同缓冲的解析推导与数值验证
Breaking Behavioral Uniformity in Traffic Flow: Analytical Derivation and Numerical Verification of Optimal Cooperative Buffering
arXiv 2610.11557 · 2026-10-09SoK：大语言模型在源代码恢复方面是否可靠？分类与实证评估
SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation
arXiv 2610.11556 · 2026-10-09联邦线性随机近似（LSA）中的两全其美：可能时提速，始终个性化
Best of Both Worlds in Federated LSA: Speedup When Possible, Personalization Always
arXiv 2610.11555 · 2026-10-09均匀生成树与行列式过程的乘积近似
Product approximations for uniform spanning trees and determinantal processes
arXiv 2610.11554 · 2026-10-09EVIE：用于视觉文档检索的证据向量感知嵌入
EVIE: Evidence-Vector-Informed Embeddings for Visual Document Retrieval
arXiv 2610.11553 · 2026-10-09用于理解部分可观测世界的安全、持久且可演进的智能体管控框架
Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
arXiv 2610.11552 · 2026-10-09在线稀疏线性回归的遗憾值的新下界与上界
New Lower Bound and Upper Bounds on the Regret for Online Sparse Linear Regression
arXiv 2610.11551 · 2026-10-09超快相干亚皮秒磁振子脉冲的演示
Demonstration of ultrafast coherent sub-picosecond magnon pulses
arXiv 2610.11550 · 2026-10-09用于微观结构生成的各向异性幂图图上的$C_4$等变流匹配
$C_4$-Equivariant Flow Matching on Anisotropic Power-Diagram Graphs for Microstructure Generation
arXiv 2610.11549 · 2026-10-09从受控预训练混合数据到代码的条件迁移
Conditional Transfer from Controlled Pretraining Mixtures to Code
arXiv 2610.11548 · 2026-10-09OX-NeRF：使用隐式神经表示从稀疏视图进行3D X射线断层扫描重建
OX-NeRF: 3D X-ray Tomography Reconstruction from Sparse Views Using Implicit Neural Representation
arXiv 2610.11547 · 2026-10-09学习协调进化搜索：优化与结构模型更新中面向动态DE-CMA-ES协调的进度感知深度强化学习
Learning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning for Dynamic DE-CMA-ES Coordination in Optimization and Structural Model Updating
arXiv 2610.11546 · 2026-10-09非阿基米德与混合设定下朱利亚集的连续性
Continuity of the Julia sets in non-archimedean and hybrid settings
arXiv 2610.11545 · 2026-10-09韵律转文本：从低通滤波语音中预测文本
Prosody-to-Text: Predicting text from low-pass filtered speech
arXiv 2610.11544 · 2026-10-09学习循环，而非仅页面：面向网页生成的基于执行的循环学习
Learning the Loop, Not Just the Page: Execution-Grounded Loop Learning for Web Generation
arXiv 2610.11543 · 2026-10-09面向多智能体大语言模型谈判的宪法门控与确定性恢复：针对有状态对抗性守门人的消融研究
Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper
arXiv 2610.11542 · 2026-10-09同位素比例作为探测中心分子区恒星形成与分子气体起源的探针
Isotopic ratios as probes of star formation and the origin of molecular gas in the Central Molecular Zone
arXiv 2610.11541 · 2026-10-09快速提取随机电路基准测试实验中的保真度衰减率
Quickly extracting fidelity decay rates in random circuit benchmarking experiments
arXiv 2610.11540 · 2026-10-09设计创意基准：衡量大语言模型生成的用户界面的创意
Design Creativity Bench: Measuring creativity in LLM-Generated UI
arXiv 2610.11539 · 2026-10-09LAIR-Net：用于表格回归的泄漏对齐脉冲残差网络
LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression
arXiv 2610.11538 · 2026-10-09一种使用量子神经网络执行流模型的高效量子电路
An Efficient Quantum Circuit for Flow Model Execution Using Quantum Neural Networks
arXiv 2610.11537 · 2026-10-09二维玻色-爱因斯坦凝聚体的物质波矢量孤子的非线性管理
Nonlinearity management of matter-wave vector solitons of Bose-Einstein condensates in two dimensions
arXiv 2610.11536 · 2026-10-09带单个入射波的无牵引力多边形障碍物的弹性波逆散射唯一性
Uniqueness in inverse elastic scattering from traction-free polygonal obstacles with a single incoming wave
arXiv 2610.11535 · 2026-10-09HAND：一种受生物启发的激活函数，可提升图像分类任务的泛化能力与样本效率
HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification
arXiv 2610.11534 · 2026-10-09幂-刘维尔厄米轨道：奇异六次振荡器与分数幂势的共同谱量化
A Power-Liouville Hermite Orbit: Common Spectral Quantization of the Singular Sextic Oscillator and Fractional-Power Potentials
arXiv 2610.11533 · 2026-10-09用于L²梯度流的保平衡指数Runge-Kutta方法的原始能量耗散的统一框架
A unified framework for original energy dissipation of equilibrium-preserving exponential Runge--Kutta methods for $L^2$ gradient flows
arXiv 2610.11532 · 2026-10-09RAGNAROK：用于鲁棒性开放关键帧雷达-视觉-运动学-惯性SLAM的雷达辅助重力归一化对齐
RAGNAROK: Radar-Aided Gravity-Normalized Alignment for Robust Open Keyframe-based Radar-Visual-Kinematic-Inertial SLAM
arXiv 2610.11531 · 2026-10-09三颗基准早型L型矮星中的气态SiO与硅酸盐云
Gaseous SiO and Silicate Clouds in Three Benchmark Early-L Dwarfs
arXiv 2610.11530 · 2026-10-09ReTeach：通过多轮反思与重试构建自教师
ReTeach: Building a Self-Teacher through Multi-Round Reflection and Retry
arXiv 2610.11529 · 2026-10-09扩散过程关于其起始位置的耦合凸性
Coupling-convexity of a diffusion with respect to its starting position
arXiv 2610.11528 · 2026-10-09AtomWorld-Mirror：面向材料动力学关键演化主干的宏步世界建模
AtomWorld-Mirror: Macro-Step World Modeling of Critical Evolution Backbones for Materials Dynamics
arXiv 2610.11527 · 2026-10-09MSGAT：用于图像-文本检索的带相似度空间融合的多头脉冲图注意力网络
MSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval
arXiv 2610.11526 · 2026-10-09你的数据库系统在生产环境中应使用硬件辅助的内存安全扩展吗？
Should Your Database Systems Use Hardware-Assisted Memory Safety Extensions in Production?
arXiv 2610.11525 · 2026-10-09基于音乐约束序列编辑的无参考歌声音高修正
Reference-Free Singing Pitch Correction via Music-Constrained Sequence Editing
arXiv 2610.11524 · 2026-10-09何时进行干预？联邦强化学习中的状态感知稀疏操纵
When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning
arXiv 2610.11523 · 2026-10-09结合风洞数据的CFD评分联合误差度量，按参与者的稳健离散度缩放（AutoCFD5案例2）
A joint error metric for scoring CFD against wind tunnel data, scaled by the robust spread of the participants (AutoCFD5 Case 2)
arXiv 2610.11522 · 2026-10-09交替多重zeta值的新型Hoffman型生成元
New Hoffman-type generators for alternating multiple zeta values
arXiv 2610.11521 · 2026-10-09
