2026-10论文中文摘要
正则化 $p(x)$-Laplacian 的几何与随机框架
Geometric and stochastic framework for a regularized $p(x)$-Laplacian
arXiv 2610.05609 · 2026-10-06Kandinsky 6.0 Video：用于同步视频和音频生成的基础模型
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
arXiv 2610.05608 · 2026-10-06差速驱动机器人的紧急避障机动
Emergency Obstacle Avoidance Maneuvers in Differential-Drive Mobile Robots
arXiv 2610.05607 · 2026-10-06探索人机交互中个性的影响：基于人类语音特征的用户-智能体同步性研究
Exploring the Effects of Personality in Human-Agent Interactions: A Study on User-Agent Synchrony with Human-based Vocalics
arXiv 2610.05606 · 2026-10-06性能可移植性研究中缺失数据的处理
Handling Missing Data in Performance Portability Studies
arXiv 2610.05605 · 2026-10-06构建用于自动驾驶研究的多传感器平台：挑战与经验教训
Building A Multi-Sensor Platform For Autonomous Driving Research: Challenges and Lessons Learned
arXiv 2610.05604 · 2026-10-06历史依赖的不稳定方向与Binder--DeMarco猜想
History-dependent unstable directions and the Binder--DeMarco conjecture
arXiv 2610.05602 · 2026-10-06你的遗忘会暴露你：识别扩散模型中被擦除的概念
Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models
arXiv 2610.05601 · 2026-10-06一种用于生物信息学特征选择的LLM在环强化学习框架
An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection
arXiv 2610.05600 · 2026-10-06无平稳矩条件下SGD的高斯极限
Gaussian Limits for SGD Without Stationary Moments
arXiv 2610.05599 · 2026-10-06当跨孤岛联邦离线时：基于有限无标注数据的新站点持续学习
When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data
arXiv 2610.05598 · 2026-10-06超越词面：面向高效语言模型的组合式分词
More Than Words: Compositional Tokenization for Efficient Language Models
arXiv 2610.05597 · 2026-10-06液滴触发的垂直强迫浴槽中的法拉第波
Droplet-triggered Faraday waves in a vertically forced bath
arXiv 2610.05596 · 2026-10-06常步长随机逼近的矩精确高斯混合
Moment-Accurate Gaussian Mixtures for Constant-Step Stochastic Approximation
arXiv 2610.05595 · 2026-10-06质子张量电荷提取中π⁰电产生截面的似然与相关性分析
Likelihood \& Correlation Analysis of $π^o$ Electroproduction for Proton Tensor Charge Extraction
arXiv 2610.05594 · 2026-10-06一个可解的量子多体问题
A solvable quantum many-body problem
arXiv 2610.05593 · 2026-10-06多单元量子电池中通过退相干擦除纠缠锁定能量
Erasure of entanglement-locked energy in multi-cell quantum batteries through decoherence
arXiv 2610.05592 · 2026-10-06重复 token 的价值是什么？多轮预训练中的缩放几何
What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining
arXiv 2610.05591 · 2026-10-06ColdDDI：评估冷启动药物-药物相互作用预测中的知识利用
ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction
arXiv 2610.05590 · 2026-10-06发送者-接收者博弈中的支付承诺
Sender-Receiver Games with Payment Commitments
arXiv 2610.05588 · 2026-10-06生成野生：面向野生动物的个体一致图像到视频生成
Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife
arXiv 2610.05587 · 2026-10-06AgentDoxx：基于网络搜索的匿名文本智能体重识别
AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search
arXiv 2610.05586 · 2026-10-06通信复杂度中最优且可验证的量子优势
Optimal and Verifiable Quantum Advantages in Communication Complexity
arXiv 2610.05585 · 2026-10-06扩展LLM推理
Expanding LLM Reasoning
arXiv 2610.05584 · 2026-10-06TacGELLO：用于3D打印遥操作主端设备的触觉接触反馈
TacGELLO: Tactile Contact Feedback for a 3D-Printed Teleoperation Leader
arXiv 2610.05583 · 2026-10-06Countryman 基与 MA$(\omega_1)$ 下的 club-同构
Countryman basis and club-isomorphisms under MA$(ω_1)$
arXiv 2610.05582 · 2026-10-06自由群和曲面群上的唯一遍历分支子集流
Uniquely Ergodic Branching Subset Currents on Free and Surface Groups
arXiv 2610.05581 · 2026-10-06带尾部约束的随机在线竞价的原始-对偶方法
A Primal-Dual Approach to Randomized Online Bidding with Tail Constraints
arXiv 2610.05580 · 2026-10-06何时构成作弊？探索自我效能感与冒充者现象在计算机专业学生学术不端认知中的作用
When Does It Become Cheating? Exploring the Roles of Self-Efficacy and the Impostor Phenomenon in Computing Students' Perceptions of Academic Dishonesty
arXiv 2610.05579 · 2026-10-06重新思考异构边缘平台上的流式感知评估
Rethinking Streaming-Perception Evaluation on Heterogeneous Edge Platforms
arXiv 2610.05578 · 2026-10-06可观测性基础模型知道什么？
What Does an Observability Foundation Model Know?
arXiv 2610.05577 · 2026-10-06韵律风格能否仅从文本中推断？来自无监督声学聚类的证据
Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters
arXiv 2610.05575 · 2026-10-06力迫公理与Aronszajn树的结构理论
Forcing axioms and the structure theory of Aronszajn trees
arXiv 2610.05574 · 2026-10-06更好的检索，有限的聚类增益：多语言公司实体消解的控制研究
Better Retrieval, Limited Clustering Gains: A Controlled Study of Multilingual Company Entity Resolution
arXiv 2610.05573 · 2026-10-06在智能体失败预测中区分任务难度与运行级失败
Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction
arXiv 2610.05572 · 2026-10-06基于场景的组合式统计模型检验用于安全规范
Scenario-Based Compositional Statistical Model Checking for Safety Specifications
arXiv 2610.05571 · 2026-10-06Poisson-GENERIC 神经算子：通过 Casimir 熵在函数空间中实现精确的度量-辛结构
Poisson-GENERIC Neural Operators: Exact Metriplectic Structure in Function Space via Casimir Entropies
arXiv 2610.05570 · 2026-10-06Factoriax：用于强化学习的GPU加速类Factorio模拟器
Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning
arXiv 2610.05569 · 2026-10-06关于 $x^{d_{r}} + x^{d_{r-1}} + \cdots + x^{d_{2}} + x^{d_{1}} + p$ 的因式分解及 C. Nicol 的一个猜想
On the factorization of $x^{d_{r}} + x^{d_{r-1}} + \cdots + x^{d_{2}} + x^{d_{1}} + p$ and a conjecture of C. Nicol
arXiv 2610.05568 · 2026-10-06关于$\phi$-弱整体维数与$\phi$-整体维数
On the $ϕ$-Weak Global Dimensions and $ϕ$-Global Dimensions
arXiv 2610.05567 · 2026-10-06终身数字孪生：面向事件驱动的终身健康状态轨迹的统一建模范式与智能体框架
LifeLong Digital Twin: A Unified Modeling Paradigm and Agent Harness for Event-Driven Lifelong Health State Trajectories
arXiv 2610.05566 · 2026-10-06四方多项式三元组：二次分类与等次数障碍
Four-square polynomial triples: quadratic classification and equal-degree obstructions
arXiv 2610.05565 · 2026-10-06借我你的眼睛：通过注意力中继实现指令感知的文本嵌入
Lend Me Your Eyes: Instruction-Aware Text Embeddings via Attention Relay
arXiv 2610.05564 · 2026-10-06G-CARB：面向组合危害的图局部化共形智能体风险预算
G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm
arXiv 2610.05563 · 2026-10-06正 $p$-秩曲线自同构群的二次界（奇特征情形）
A Quadratic Bound for Automorphism Groups of Curves of Positive $p$-Rank in Odd Characteristic
arXiv 2610.05562 · 2026-10-06超越单一扰动：多属性度量差分隐私的异构机制设计
Beyond Monolithic Perturbation: Heterogeneous Mechanism Design for Multi-Attribute Metric Differential Privacy
arXiv 2610.05561 · 2026-10-06广义交叉多胞形的析取凸包进一步研究
More on Disjunctive Convex Hulls of Generalized Cross Polytopes
arXiv 2610.05560 · 2026-10-06截断二元交叉熵：面向序列推荐的高效大词表损失与梯度算子
Cut Binary Cross Entropy: Efficient Large-Vocabulary Loss and Gradient Kernels for Sequential Recommendation
arXiv 2610.05559 · 2026-10-06Dobrushin 界在注意力展开上的等式条件及其在训练后变换器中的成立频率
An equality condition for the Dobrushin bound on attention rollout and how often it holds in trained transformers
arXiv 2610.05558 · 2026-10-06同步蒙特卡洛动力学中的Sherrington-Kirkpatrick模型的Parisi解
Parisi's solution of the Sherrington--Kirkpatrick model from synchronous Monte Carlo dynamics
arXiv 2610.05557 · 2026-10-06
