2026-10论文中文摘要
M3SunAgent：用于度量深度估计与3D视觉定位的单目3D空间理解智能体
M3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual Grounding
arXiv 2610.07982 · 2026-10-07高阶模型是否因高阶原因而获胜？重新思考超图学习中的性能提升
Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph Learning
arXiv 2610.07981 · 2026-10-07通过统一晶体塑性-断裂框架揭示晶间与穿晶蠕变开裂之间的机制转变
Mechanistic transition between inter- and trans-granular creep cracking via a unified crystal plasticity-fracture framework
arXiv 2610.07980 · 2026-10-07从修订后果中学习：基于事后元经验蒸馏的自我改进智能体
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents
arXiv 2610.07979 · 2026-10-07次线性期望下由时空$G$-白噪声驱动的随机波动方程
Stochastic wave equations driven by space-time $G$-white noise under sublinear expectation
arXiv 2610.07978 · 2026-10-07LISA的时频分析：银河系前景调制
Time-Frequency Analysis for LISA: Galactic Foreground Modulation
arXiv 2610.07977 · 2026-10-07量化运营商侧5G/O-RAN配置文件的隐私姿态
Quantifying the Privacy Posture of Operator-Side 5G/O-RAN Profiles
arXiv 2610.07976 · 2026-10-07利用爱因斯坦望远镜对中子星状态方程进行可扩展的序贯推断
Scalable and sequential inference of the neutron star equation of state with the Einstein Telescope
arXiv 2610.07975 · 2026-10-07构型而非阈值：OECD中中东欧成员国的中等收入陷阱
Configurations, not thresholds: the middle-income trap in the CEE members of the OECD
arXiv 2610.07974 · 2026-10-07在对数凹随机效用模型中从人类反馈中学习排序
Learning a Ranking from Human Feedback in Log-Concave Random Utility Models
arXiv 2610.07973 · 2026-10-07智能体能否为所有人服务？个性化用户界面中移动图形用户界面智能体的跨用户可靠性
Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces
arXiv 2610.07972 · 2026-10-07概率邻居选择与确认偏误在有界置信模型中的竞争
Probabilistic neighbors' selection competes with confirmation bias in a bounded confidence model
arXiv 2610.07971 · 2026-10-07用于可验证数字馆藏对象的私有IPFS数据保护区
A Private IPFS Data Sanctuary for Verifiable Digital Collection Objects
arXiv 2610.07970 · 2026-10-07EmbodiedSmith：通过仿真中的递归自我改进飞轮扩展具身数据
EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation
arXiv 2610.07969 · 2026-10-07Chen-Raspaud 猜想 k=4 情形的独立计算机辅助证明
An independent computer-assisted proof of the Chen-Raspaud conjecture for k=4
arXiv 2610.07968 · 2026-10-07DecepEval：评估LLM智能体欺骗行为的基准
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
arXiv 2610.07967 · 2026-10-07基于VAE的音频解码器中的特征编码：输入、深度和分布的影响
Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution
arXiv 2610.07966 · 2026-10-07优化引力波探测器中的拉盖尔-高斯模式干涉测量：通过模式简并破除
Optimizing Laguerre-Gaussian Mode Interferometry in Gravitational-Wave Detectors through Modal Degeneracy Breaking
arXiv 2610.07965 · 2026-10-07长程非平衡关联作为热力学速度计
Long-Range Nonequilibrium Correlations as a Thermodynamic Speedometer
arXiv 2610.07964 · 2026-10-07Lévy 符号收敛下半线性外部 Dirichlet 问题解的稳定性
Stability of Solutions to Semilinear Exterior Dirichlet Problems under Convergence of Lévy Symbols
arXiv 2610.07963 · 2026-10-07ReGraph："什么"与"哪里"双视觉流中涌现泛化的计算解释
ReGraph: A Computational Account of Emergent Generalization in the "what" and "where" Dual Visual Streams
arXiv 2610.07962 · 2026-10-07IronMan：面向机器人操作的信息约束视频-动作学习
IronMan: Information-Constrained Video-Action Learning for Robot Manipulation
arXiv 2610.07961 · 2026-10-07从交付到有状态探索：重新思考智能体搜索的索引
From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search
arXiv 2610.07960 · 2026-10-07在PoS治理中奖励知情投票
Rewarding Informed Voting in PoS Governance
arXiv 2610.07959 · 2026-10-07DensiTok：让前馈3D高斯泼溅看到比给定更多的视图
DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given
arXiv 2610.07958 · 2026-10-07矩阵函数的Wiener--Hopf分解的规范化
Normalisation of Wiener--Hopf Factorisation for Matrix Functions
arXiv 2610.07957 · 2026-10-07实用多层马尔可夫链蒙特卡洛的高效子采样率选择
Efficient subsampling-rate selection for practical Multilevel Markov chain Monte Carlo
arXiv 2610.07956 · 2026-10-07对角Specht理想及其簇
Diagonal Specht ideals and their varieties
arXiv 2610.07955 · 2026-10-07重新审视基于语言的轨迹预测中的数值预测模型
Revisiting Numerical Forecasting Models for Language-Based Trajectory Prediction
arXiv 2610.07954 · 2026-10-07在线审核中的System One模型基准测试
Benchmarking System One Models in Online Moderation
arXiv 2610.07953 · 2026-10-07学习超越连续介质区域的广义纳维-斯托克斯模型
Learning a generalized Navier-Stokes model beyond the continuum regime
arXiv 2610.07952 · 2026-10-07一种用于同时监测脊髓氧合、灌注和代谢的多模态高光谱与激光散斑成像平台
A Multimodal Hyperspectral and Laser Speckle Imaging Platform for Simultaneous Monitoring of Spinal Cord Oxygenation, Perfusion and Metabolism
arXiv 2610.07951 · 2026-10-07$C^1$迭代函数系统非齐次吸引子的上盒维数
Upper box dimension of inhomogeneous attractors of $C^1$ iterated function systems
arXiv 2610.07950 · 2026-10-07当未来一致时提交：面向机器人操作的结果感知自适应动作分块
Commit While Futures Agree: Consequence-Aware Adaptive Action Chunking for Robot Manipulation
arXiv 2610.07949 · 2026-10-07置信推理图：面向LLM智能体的结构化置信估计
Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents
arXiv 2610.07948 · 2026-10-07混沌吸积（仍）可以解释早期超大质量黑洞的增长
Chaotic accretion can (still) explain early supermassive black hole growth
arXiv 2610.07947 · 2026-10-07适应视觉-语言-动作模型以应对执行过程中的未知视觉干扰
Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution
arXiv 2610.07946 · 2026-10-07$Q\text{--}P$ 空间与中间 Hausdorff 型结构的一般框架
A General Framework for $Q\text{--}P$ Spaces and Intermediate Hausdorff-Type Structures
arXiv 2610.07945 · 2026-10-07超声速杂质与玻色凝聚体强耦合的极化子响应
Polaronic Response of a Supersonic Impurity Strongly Coupled to a Bose Condensate
arXiv 2610.07944 · 2026-10-07森林独立多项式的单峰性
Unimodality of Forest Independence Polynomials
arXiv 2610.07943 · 2026-10-07n型4H-SiC中III族受主的第一性原理建模及其潜在寿命限制效应
First principles modeling of group-III acceptors and their potential lifetime-limiting effects in n-type 4H-SiC
arXiv 2610.07942 · 2026-10-07UltraDiff：超声中的可微光线追踪用于形状优化
UltraDiff: Differentiable Ray Tracing in Ultrasound for Shape Optimization
arXiv 2610.07941 · 2026-10-07循环语言模型的混合潜在注意力
Hybrid Latent Attention for Looped Language Models
arXiv 2610.07940 · 2026-10-07CCDF：面向真实世界监控视频的深度伪造检测基准数据集
CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance Footage
arXiv 2610.07939 · 2026-10-07广义Matheron变分隐式过程
Generalized Matheron Variational Implicit Processes
arXiv 2610.07938 · 2026-10-07利用四象限方法评估Redpine Science
Leveraging a four-quadrant approach for evaluating Redpine Science
arXiv 2610.07937 · 2026-10-07伪词作为探针：大型语言模型对支配人类伪词处理的亚词汇敏感性表现甚微
Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing
arXiv 2610.07936 · 2026-10-07SIGMA：从模型规范中实现自我改进的对齐泛化
SIGMA: Self-Improving Alignment Generalization from a Model Spec
arXiv 2610.07935 · 2026-10-07守恒量子大气对黑洞几何的视界尺度修正
Horizon-Scale Corrections to Black Hole Geometry from a Conserved Quantum Atmosphere
arXiv 2610.07934 · 2026-10-07修正贝塞尔函数乘积及其对数导数的尖锐双侧界
Sharp two-sided bounds for the product of modified Bessel functions and for its logarithmic derivative
arXiv 2610.07933 · 2026-10-07
