2026-10论文中文摘要
基于核自编码器的Koopman嵌入数据驱动学习的双层优化方法
Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders
arXiv 2610.12370 · 2026-10-09具身图灵机：用于机器人递归自我改进的有状态代码
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
arXiv 2610.12369 · 2026-10-09LiteNWM：用于野外机载视觉导航的高效潜在世界模型
LiteNWM: Efficient Latent World Models for Onboard Visual Navigation in the Wild
arXiv 2610.12368 · 2026-10-09应蒸馏哪种技能？SGUID：为模型-技能协同进化选择紧凑技能库
Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution
arXiv 2610.12367 · 2026-10-09有向分形渗流及其非利普希茨变体
Directed fractal percolation and non-Lipschitz variants
arXiv 2610.12366 · 2026-10-09纯损耗信道的能量受限双向容量
Energy-constrained two-way capacities of the pure-loss channel
arXiv 2610.12365 · 2026-10-0916亏格曲线的模空间是单有理的
The moduli space of curves of genus 16 is uniruled
arXiv 2610.12364 · 2026-10-09HANS：用于含噪混合文档解析的手写答题卡数据集
HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing
arXiv 2610.12363 · 2026-10-09缩小对抗马尔可夫决策过程（MDP）中策略优化的视界差距
Closing the Horizon Gap in Policy Optimization for Adversarial MDPs
arXiv 2610.12362 · 2026-10-09被引用但未被参考：法律思维链忠实性的反事实审计
Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness
arXiv 2610.12361 · 2026-10-09准确但不谦逊：知识冲突下大语言模型智能体的认知谦逊评估
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
arXiv 2610.12360 · 2026-10-09双中子星并合后早期星云中维恩火球的漏斗泄漏
Funnel Leakage of the Wien Fireball in the Early Nebula after a Binary Neutron Star Merger
arXiv 2610.12359 · 2026-10-09布尔立方体上的子空间不确定性与尖锐采样阈值
Subspace Uncertainty and Sharp Sampling Thresholds on the Boolean Cube
arXiv 2610.12358 · 2026-10-09Shamir秘密共享的改进局部泄漏弹性与最坏情况最优多项式交集
Improved Local Leakage Resilience of Shamir Secret Sharing and Worst-Case Optimal Polynomial Intersection
arXiv 2610.12357 · 2026-10-09对伽马射线 blazars 中年尺度稳定调制的形态学搜索
A morphological search for stable year-scale modulation in gamma-ray blazars
arXiv 2610.12356 · 2026-10-09为视觉语言模型的空间推理提炼路由式3D特权
Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models
arXiv 2610.12355 · 2026-10-09带漂移的布朗运动在受限L²范数条件下的情况
Brownian motion with drift conditioned to have restricted $L^2$-norm
arXiv 2610.12354 · 2026-10-09无参数收敛损失的渐近消失激励
Asymptotically Vanishing Excitation Without Loss of Parameter Convergence
arXiv 2610.12353 · 2026-10-09有色琼斯函数无法确定任何有色链——古尔德多项式
The Colored Jones Function does not determine any colored Links--Gould polynomial
arXiv 2610.12352 · 2026-10-09负曲率度量的稀疏性的普遍性
Prevalence of sparsity for negatively curved metrics
arXiv 2610.12351 · 2026-10-09面板信息矩阵检验
The Panel Information Matrix Test
arXiv 2610.12350 · 2026-10-09SplitJEPA：无需重构学习不变与变异性潜在世界
SplitJEPA: Learning Invariant and Variant Latent Worlds without Reconstruction
arXiv 2610.12349 · 2026-10-09在混合量子系统中构建大且具有结构的无退相干子空间
Constructing Large and Structured Decoherence-Free Subspaces in Hybrid Quantum Systems
arXiv 2610.12348 · 2026-10-09同源球面的着色问题
Coloring graphs of homologous spheres
arXiv 2610.12347 · 2026-10-09随机交替投影中的体积采样与谱均衡
Volume Sampling and Spectral Equalization in Randomized Alternating Projections
arXiv 2610.12346 · 2026-10-09克服先验障碍：长尾分布下的监督微调
Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution
arXiv 2610.12345 · 2026-10-09高维簇上的几何阿贝尔截面
Geometrically Abelian Sections on Higher-Dimensional Varieties
arXiv 2610.12344 · 2026-10-09推理驱动的视觉编辑
Reasoning-Informed Visual Editing
arXiv 2610.12343 · 2026-10-09动态模式自适应控制中基于参考调节器的约束执行
Constraint Enforcement via Reference Governor in Dynamic Mode Adaptive Control
arXiv 2610.12342 · 2026-10-09AI智能体能学习登顶吗？在长期运行的游戏智能体竞赛中评估启发式学习
Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
arXiv 2610.12341 · 2026-10-09环境离散扩散：在合适的时间使用错误的数据实现数据高效学习
Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient Learning
arXiv 2610.12340 · 2026-10-09哈伯德模型赝能隙区域中的真实与虚假费米面及其随掺杂和温度的转变
True vs false Fermi surfaces in the Pseudogap regime and their transformation with doping and temperature in the Hubbard Model
arXiv 2610.12339 · 2026-10-09VFold：感知对称性的跨层值缓存压缩
VFold: Symmetry-Aware Cross-Layer Value Cache Compression
arXiv 2610.12338 · 2026-10-09ContiLNN：用液体神经网络缓解医学图像复原中的切片采样不连续性
ContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration
arXiv 2610.12337 · 2026-10-09asdex：JAX中的自动稀疏微分
asdex: Automatic Sparse Differentiation in JAX
arXiv 2610.12336 · 2026-10-09对数相关势中布朗粒子的反常标度极限
Anomalous scaling limit of a Brownian particle in a log-correlated potential
arXiv 2610.12335 · 2026-10-09非均匀多体中微子快味转换的量子协同设计
Quantum Co-Design of Inhomogeneous Many-Body Neutrino Fast Flavor Transformation
arXiv 2610.12334 · 2026-10-09RiCo：基于局部接触推理的刚体交互神经模拟
RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning
arXiv 2610.12333 · 2026-10-09用于治疗效果估计的预测驱动数据融合
Prediction-Powered Data Fusion for Treatment Effect Estimation
arXiv 2610.12332 · 2026-10-09κ-闵可夫斯基空间中的波包渐近行为
Wave packets asymptotics in $κ$-minkowski space
arXiv 2610.12331 · 2026-10-09特征标圈与超几何族的不规则性Gevrey滤过
Characteristic cycles and the Gevrey filtration of irregularity in hypergeometric families
arXiv 2610.12330 · 2026-10-09有限单群的普通$G$-可置换子群
Ordinary $G$-permutable subgroups of finite simple groups
arXiv 2610.12329 · 2026-10-09具有最优神谕复杂度的复合在线到非凸转换
Composite Online-to-Nonconvex Conversion with Optimal Oracle Complexity
arXiv 2610.12328 · 2026-10-09SparseDecoding：面向准确高效的大语言模型推理的解码感知剪枝方法
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
arXiv 2610.12327 · 2026-10-09关于麦克唐纳函数的纳扎罗夫-斯克莱宁（Nazarov-Sklyanin）Lax算子
On the Nazarov-Sklyanin Lax operator for Macdonald functions
arXiv 2610.12326 · 2026-10-09先验还是反馈？大语言模型在适配神经算子时依赖什么
Prior or Feedback? What an LLM Uses When Adapting Neural Operators
arXiv 2610.12325 · 2026-10-09基于谱选择的凸安全滤波用于非凸安全集
Convex Safety Filtering via Spectral Selection for Nonconvex Safe Sets
arXiv 2610.12324 · 2026-10-09O型巨星英仙座ξ的自转周期：周期与循环变异性共存，一颗弱磁候选星
Rotation period of the O giant xi Persei: Coexistence of cyclic and periodic variability. A weakly magnetic candidate star
arXiv 2610.12323 · 2026-10-09JWST CAPERS：甚高红移星系候选体的光谱学评估
JWST CAPERS: Spectroscopic evaluation of very high redshift galaxy candidates
arXiv 2610.12322 · 2026-10-09公共物品困境中多智能体学习产生的空间模式形成
Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas
arXiv 2610.12321 · 2026-10-09
