2026-10论文中文摘要
具有对合性质的正式矩阵环
Formal Matrix Rings with the Involution Property
arXiv 2610.04709 · 2026-10-06基于自适应单位分解混合专家网络的局部算子学习
Localized Operator Learning with Adaptive Partition-of-Unity Mixture-of-Expert Networks
arXiv 2610.04708 · 2026-10-06引力常数测量中的协方差缩放与双模式扭矩诊断
Covariance scaling and a dual-mode torque diagnostic in measurements of the gravitational constant
arXiv 2610.04707 · 2026-10-06VoCa：为基于语音的对话代理设计语音-画布交互
VoCa: Designing Speech-Canvas Interaction for Voice-Based Conversational Agents
arXiv 2610.04706 · 2026-10-06神经多样性感知的多模态情感计算用于神经发育评估：从常模参照分类到情境敏感决策支持
Neurodiversity-Aware Multimodal Affective Computing for Neurodevelopmental Assessment: From Norm-Referenced Classification to Context-Sensitive Decision Support
arXiv 2610.04705 · 2026-10-06剥离阿贝尔任意子与增殖相变
Peeling off Abelian Anyons and Proliferation Transitions
arXiv 2610.04704 · 2026-10-06学习漂移模型的判别几何
Learning Discriminative Geometry for Drifting Models
arXiv 2610.04703 · 2026-10-06超越典范界的循环自同构
Cyclic automorphisms beyond the canonical bound
arXiv 2610.04702 · 2026-10-06测试时训练作为机器人策略的残差记忆
Test-Time Training as Residual Memory for Robot Policies
arXiv 2610.04701 · 2026-10-06解耦、净化与统一：面向联邦医学分割的语义-结构原型学习
Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation
arXiv 2610.04700 · 2026-10-06不可自决：LLMs 无法划定智能体验证器可检查的边界
Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check
arXiv 2610.04699 · 2026-10-06LOFAR十米波巡天（LoDeSS）I. 巡天描述与首次数据发布
The LOFAR Decametre Sky Survey (LoDeSS) I. Survey description and first data release
arXiv 2610.04698 · 2026-10-06效率与鲁棒性划分循环网络中记忆的解空间
Efficiency and robustness partition the solution space for memory in recurrent networks
arXiv 2610.04697 · 2026-10-06分数校准流：用于从非归一化密度采样及其在生成式在线强化学习中的应用
Score-Calibrated Flow for Sampling from Unnormalized Densities with Applications to Generative Online Reinforcement Learning
arXiv 2610.04696 · 2026-10-06低保真FDM谱引导的神经特征值求解器
Low-Fidelity FDM Spectral Guidance for Neural Eigenvalue Solvers
arXiv 2610.04695 · 2026-10-06一般相空间上的稳定子码
Stabilizer codes over general phase spaces
arXiv 2610.04694 · 2026-10-06Penumbra：面向监管义务的样本高效对抗性搜索
Penumbra: Sample-Efficient Adversarial Search for Regulatory Obligations
arXiv 2610.04693 · 2026-10-06约束系统的替代哈密顿与拉格朗日方法
Alternative Hamiltonian and Lagrangian Approaches for Constrained Systems
arXiv 2610.04692 · 2026-10-06RAGStress：一个用于评估知识库退化下检索增强生成的受控基准
RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation
arXiv 2610.04691 · 2026-10-06SepRQ：通过无掩码、多尺度源分离的自监督语音混合表示学习
SepRQ : Self-Supervised Speech Mixture Representation Learning via Mask-Free, Multi-Scale Source Separation
arXiv 2610.04690 · 2026-10-06当稿件生产成本低廉时，投稿配额作为自我筛选机制
Submission quotas as self-screening when manuscript production is cheap
arXiv 2610.04688 · 2026-10-06辩论何时有帮助：多智能体推理中的提案供给与验证感知读出
When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning
arXiv 2610.04686 · 2026-10-06关于求解线性最小二乘问题的随机批量采样坐标下降方法
On randomized batch-sampling coordinate descent methods for solving linear least-squares problems
arXiv 2610.04685 · 2026-10-06交替磁体中受阻与量子自旋霍尔拓扑的电子-声子调控
Electron-phonon control of obstructed and quantum spin Hall topology in an altermagnet
arXiv 2610.04684 · 2026-10-06引导语音语言模型：通过对比激活添加实现免训练任务特化
Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition
arXiv 2610.04683 · 2026-10-06电子-离子对撞机电子束准直器的设计
Design of the Electron-Beam Collimator for the Electron-Ion Collider
arXiv 2610.04682 · 2026-10-06COMPASS：带有自动选择和评分的彗星物体测量流程
COMPASS: Comet Object Measurement Pipeline with Automated Selection and Scoring
arXiv 2610.04680 · 2026-10-06少量小素数足以覆盖单位群
Few small primes suffice to cover unit groups
arXiv 2610.04678 · 2026-10-06带相依残差曲线的惩罚函数对函数回归中的估计与推断
Estimation and inference in penalized function-on-function regression with dependent residual curves
arXiv 2610.04677 · 2026-10-06通过迭代零空间投影提取人格子空间用于调制
Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation
arXiv 2610.04676 · 2026-10-06Johnson 图中的支配与全支配
Domination and Total Domination in Johnson graphs
arXiv 2610.04675 · 2026-10-06密钥化预言机的不可区分性提升、压缩理想密码及其更多应用
Indistinguishability Lifting for Keyed Oracles, Compressed Ideal Cipher, and More Applications
arXiv 2610.04674 · 2026-10-06Christ-Journé型奇异积分的逐点收敛性
On pointwise convergence of singular integrals of Christ-Journé type
arXiv 2610.04673 · 2026-10-06MASBench：部分可观测性下基于LLM的多智能体协作基准测试
MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability
arXiv 2610.04672 · 2026-10-06向群体提出正确的问题：用于联邦学习的偏差消除权重
Asking the Crowd the Right Question: Bias-Cancelling Weights for Federated Learning
arXiv 2610.04671 · 2026-10-06遗忘的热带几何视角：用于知识保持微调的逐单元投影器
A Tropical Geometry View of Forgetting: A Per-Unit Projector for Knowledge-Preserving Fine-Tuning
arXiv 2610.04670 · 2026-10-06日冕洞太阳风从其太阳起源到日球层的实测能量交换
Measured energy exchange in coronal hole solar wind from its solar origins to the heliosphere
arXiv 2610.04669 · 2026-10-06网络模块度的精确计算：分支定界方法
Exact computation of the network modularity with branch-and-bound
arXiv 2610.04668 · 2026-10-06量子擦除信道上的量子态不经意传输
Quantum-State Oblivious Transfer over Quantum Erasure Channels
arXiv 2610.04667 · 2026-10-06相关性决定浅层电路的优势
Correlations decide a shallow-circuit advantage
arXiv 2610.04666 · 2026-10-06面向Lattice和Hohlraum基准的线性辐射输运高效神经代理模型
Efficient Neural Surrogates for Linear Radiation Transport on the Lattice and Hohlraum benchmarks
arXiv 2610.04665 · 2026-10-06FLASHSWIN：利用内存高效注意力解锁Swin视觉Transformer中的大窗口与密集令牌
FLASHSWIN: Unlocking Large Windows and Dense Tokens in Swin Vision Transformers with Memory Efficient Attention
arXiv 2610.04664 · 2026-10-06自能中的极点是否意味着Luttinger定理的违反？
Does a pole in the self-energy imply a violation of the Luttinger theorem?
arXiv 2610.04663 · 2026-10-06可微三值时序逻辑语义与多项式代理网络
Differentiable Ternary Temporal Logic Semantics with Polynomial Surrogate Networks
arXiv 2610.04662 · 2026-10-06医疗物联网的后量子认证协议
Post-Quantum Authentication Protocol for Internet of Medical Things
arXiv 2610.04661 · 2026-10-06图的新近最大定向直径
The asymptotic maximum oriented diameter of graphs
arXiv 2610.04660 · 2026-10-06PermVLA：分解顺序作为VLA学习的正则化器
PermVLA: Factorization Order as a Regularizer for VLA Learning
arXiv 2610.04659 · 2026-10-06RETRACE：从纠缠的修复历史到可复用的CI修复经验
RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair
arXiv 2610.04658 · 2026-10-06有向图的路径拉普拉斯编码
Path Laplacian Encodings for Directed Graphs
arXiv 2610.04657 · 2026-10-06可变制造公差下弹簧设计的鲁棒优化
Robust Optimization of Spring Design under Variable Manufacturing Tolerances
arXiv 2610.04656 · 2026-10-06
