2026-09论文中文摘要
时间网络中的中心性度量：批判性与比较性综述
Centrality Measures in Temporal Networks: A Critical and Comparative Survey
arXiv 2609.00011 · 2026-09-02建立关联：从意见领袖影响到标准关联测度
Bridging Dependence: From Opinion Leader Influence to Standard Correlation Measures
arXiv 2609.00010 · 2026-09-02迈向AI的社会心理学：语言模型智能体再现类人类的最小群体偏见
Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias
arXiv 2609.00009 · 2026-09-02大规模网络中的核心-外围识别
Core-periphery identification in massive networks
arXiv 2609.00008 · 2026-09-02在支持实物交互与触控笔的多表面环境（MSE）中协同 eliciting 用于地理空间数据探索的手势
Collaboratively Eliciting Gestures for Geospatial Data Exploration on an MSE with Tangibles and Styluses
arXiv 2609.00007 · 2026-09-02harness工程：编码智能体的剖析、架构与演进——对十一个系统的源代码研究
Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems
arXiv 2609.00006 · 2026-09-02基于指令微调小型语言模型的渐进式老年金融诈骗增量风险评估
Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models
arXiv 2609.00005 · 2026-09-02带随机需求时间的多品种容量受限批量问题的离散时间马尔可夫决策过程建模
Discrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing
arXiv 2609.00004 · 2026-09-02I-CARE：针对文本到图像模型的可控、多样且具代表性的遗忘场景中与干扰相关现象的分析
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models
arXiv 2609.00003 · 2026-09-02HyperWorld：超图结构化状态序列化改进学习型文本世界模型
HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Models
arXiv 2609.00002 · 2026-09-02基于改进粒子群优化的模糊PID温度控制策略研究
Research on Optimized Fuzzy PID Temperature Control Strategy Based on Improved Particle Swarm Optimization
arXiv 2609.00001 · 2026-09-02超越人类监督扩展大型推理模型：通往超级智能的路径
Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence
arXiv 2608.31075 · 2026-09-02纯无限性转移问题
The pure infiniteness transfer problem
arXiv 2608.30906 · 2026-09-02统计力学中的弛豫问题
On the relaxation problem in statistical mechanics
arXiv 2608.30871 · 2026-09-02非平衡双珠系统中的惯性驱动信息流与对称破缺
Inertia-Driven Information Flow and Symmetry Breaking in a Nonequilibrium Two-Bead System
arXiv 2608.30849 · 2026-09-02具有临界空间相关性的二维定向聚合物的自由能与相变
Free energy and phase transition for 2D directed polymers with critical spatial correlations
arXiv 2608.30829 · 2026-09-02TopoCompress：基于图连接语义轨迹的长上下文压缩
TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories
arXiv 2608.30811 · 2026-09-02自回归马赛克：探测仅文本语言模型的二维空间推理能力
Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models
arXiv 2608.30751 · 2026-09-02多维拉格朗日谱的密度
Density of the multidimensional Lagrange spectrum
arXiv 2608.30735 · 2026-09-02校准小型语言模型以进行声明的核查价值检测
Calibrating Small Language Models for Claim Check-Worthiness Detection
arXiv 2608.30731 · 2026-09-02BiG-SURE - 用于大语言模型语义不确定性与可靠性估计的二分图
BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs
arXiv 2608.30646 · 2026-09-02用于指称图像分割与指称的高成本效益主动学习
Cost-efficient Active Learning for Referring Image Segmentation and Grounding
arXiv 2608.30621 · 2026-09-02通用常微分方程与暖雨过程的参数化
Universal ordinary differential equations and the parameterization of warm-rain processes
arXiv 2608.30610 · 2026-09-02UBASE：字节跳动万亿级向量数据管理的AI搜索引擎
ByteX: A Unified AI Search Engine at ByteDance
arXiv 2608.30607 · 2026-09-02等宽曲线与勒贝格覆盖问题
Curves of constant width and Lebesgue's covering problem
arXiv 2608.30538 · 2026-09-02基于LePHARE的Vera C. Rubin天文台活动星系核测光红移研究
Photometric redshifts for active galactic nuclei with LePHARE for the Vera C. Rubin Observatory
arXiv 2608.30494 · 2026-09-02仅靠图证据是不够的：诊断图增强大型语言模型中的原生解码器使用情况
Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs
arXiv 2608.30437 · 2026-09-02从元启发式算法到精确方法：面向多目标医护人员排班的CP-SAT方法
From Metaheuristics to Exact Methods: A CP-SAT Approach for Multi-Objective Healthcare Workforce Scheduling
arXiv 2608.30419 · 2026-09-02DOBI：基于 spare 关节招募的动态机会型身体输入，用于免手持扩展现实（XR）
DOBI: Dynamic Opportunistic Body Input via Spare Joint Recruitment for Hands-Free XR
arXiv 2608.30341 · 2026-09-02惰性接地：用事实证据攻击搜索智能体
Lazy Grounding: Attacking Search Agents with Factual Evidence
arXiv 2608.30303 · 2026-09-02碲多氢化物的超导性：Tc高于90K
Superconductivity of Tellurium Polyhydride with Tc above 90K
arXiv 2608.30139 · 2026-09-02Arkios：从零训练的开放英尼双语语言模型，带有天城文感知分词器
Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer
arXiv 2608.30092 · 2026-09-02由结构因子计算化学势：II. 带电多组分混合物
Chemical potentials from structure factors: II. Charged multi-component mixtures
arXiv 2608.30060 · 2026-09-02避免Canon排列中包含三个不同字母的模式
Avoiding patterns with three distinct letters in Canon permutations
arXiv 2608.30002 · 2026-09-02XQDT：带反馈信号的可解释定量数据-文本对齐指标
XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals
arXiv 2608.29948 · 2026-09-02REIGN：采用集成引导网络的翻新嵌入用于高效上下文长度扩展
REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling
arXiv 2608.29899 · 2026-09-02当历史是多模态时：重新思考长视野智能体的上下文管理
When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents
arXiv 2608.29897 · 2026-09-02HiVe：基于分层垂直混合专家的多任务学习，超越静态提示
HiVe: Beyond Static Prompts for Multitask Learning via Hierarchy-based Vertical Mixture-of-Experts
arXiv 2608.29790 · 2026-09-02硅中谷自由度介导的本征Dresselhaus自旋-轨道耦合
Valley-Enabled Intrinsic Dresselhaus Spin-Orbit Coupling in Silicon
arXiv 2608.29785 · 2026-09-02InteractBench：针对未公开信息下的竞赛编程任务评估大语言模型（LLM）
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
arXiv 2608.29632 · 2026-09-02OASIS：针对硬标签黑盒文本攻击优化攻击者序列
OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks
arXiv 2608.29568 · 2026-09-02零条件下三维非线性波动方程的非时衰减全局经典解
Non-time-decaying global classical solutions to nonlinear wave equations in 3D under the null condition
arXiv 2608.29500 · 2026-09-02二次Hessian方程的内部$C^{2,α}$正则性
Interior $C^{2,α}$ Regularity for the Quadratic Hessian Equation
arXiv 2608.29484 · 2026-09-02推理模型的思维链忠实性随偏好线索的传递位置与方式变化
Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered
arXiv 2608.29464 · 2026-09-02三次有理球面映射：尖锐分母区域与Gram标准型
Degree-Three Rational Sphere Maps: Sharp Denominator Region and Gram Normal Forms
arXiv 2608.29451 · 2026-09-02代码块中魔法的资源代价
The resource cost of magic in a code block
arXiv 2608.29438 · 2026-09-02旋转矩阵上的Kac游走在Θ(n²)步内混合：一项由AI发现的证明
Kac's Walk on Rotation Matrices Mixes in $\boldsymbol{Θ(n^2)}$ Steps: A Proof Discovered with AI
arXiv 2608.29403 · 2026-09-02FIREQ：用于读出和量子比特控制的FPGA仪器
FIREQ: FPGA Instrumentation for Readout and Qubit control
arXiv 2608.29399 · 2026-09-02k-Hessian方程整解的刘维尔型刚性结果
A Liouville type rigidity result for entire solutions of the $k$-Hessian equation
arXiv 2608.29392 · 2026-09-02验证FKG.in：大语言模型增强的印度食品知识的合理性评估
Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge
arXiv 2608.29249 · 2026-09-02
