2026-08论文中文摘要
NeuroForge：一个具有校准物理残差信任的自校正、几何原生神经CFD引擎
NeuroForge: Self-Auditing Neural CFD Surrogates with Calibrated Physics-Residual Trust
arXiv 2607.10333 · 2026-08-26四维安德森模型：临界随机偏微分方程的一个案例研究
The four-dimensional Anderson model: a case study for critical SPDEs
arXiv 2607.10105 · 2026-08-26通过交叉相关评估UNIONS莱曼断点星系的大规模角聚类
Assessing the large-scale angular clustering of UNIONS Lyman Break Galaxies via cross-correlations
arXiv 2607.09943 · 2026-08-26合作博弈的非线性公理归因
Nonlinear Axiomatic Attribution for Cooperative Games
arXiv 2607.09869 · 2026-08-26基于暗能量光谱仪第二次数据发布（DESI DR2）对 DGP 模型的宇宙学限制
Cosmological Constraints on the DGP Model in light of DESI DR2 2025 Data
arXiv 2607.09240 · 2026-08-26机器学习在桌面角色扮演游戏设计中怪物等级预测的应用
Application of machine learning to monster level prediction in tabletop RPG game design
arXiv 2607.09196 · 2026-08-26在CLIC的高能区增强对FCNC顶夸克衰变 \(t\to cH\) 和 \(t\to cS\) 的敏感性
Enhancing the sensitivity to FCNC top decays $t\to cH $ and $t\to cS $ in the boosted regime at CLIC
arXiv 2607.09154 · 2026-08-26Eluna：一个用于通过推理和任务执行实现仓库运营自动化的智能语言模型系统
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
arXiv 2607.08960 · 2026-08-26通过代数哈希连接和大规模离散全球网格加速多边形内点谓词
Accelerating Point-in-Polygon Predicates via Algebraic Hash-Joins and Discrete Global Grids at Scale: An interactive benchmark
arXiv 2607.08956 · 2026-08-26爱因斯坦引力的自洽精确解：金氏（2,3,0）暗物质晕中的黑洞
Exact Einsteinian Black Hole Solution in Dark Matter Environment
arXiv 2607.08792 · 2026-08-26低延迟系统中的工具制作与自我进化大语言模型智能体
Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems
arXiv 2607.08010 · 2026-08-26利用同步协变量和滞后特征进行北京PM2.5的临近预报：模型比较与变量选择稳定性
Same-Hour Estimation and Multi-Horizon Forecasting of PM2.5 in Beijing: Model Comparison and Feature-Group Contributions
arXiv 2607.07279 · 2026-08-26具有参与隐私的持续学习：一种可审计的缓冲聚合方法
Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe
arXiv 2607.07209 · 2026-08-26校准家族过拟合：为何可信破坏监测器不能跨谱系转移
Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
arXiv 2607.06596 · 2026-08-26大亏格随机双曲曲面上同调类中的闭测地线
Closed geodesics in homology classes on random hyperbolic surfaces of large genus
arXiv 2607.06263 · 2026-08-26作为超级小区的高空平台站：实现蜂窝网络中的覆盖和容量载波关闭
HAPS as a Hypercell: Enabling Coverage and Capacity Carrier Shutdown in Cellular Networks
arXiv 2607.06072 · 2026-08-26一种新的 M5 膜矩阵模型？
A Novel Matrix Model for the M5-brane?
arXiv 2607.05490 · 2026-08-26不要单独提交：扩散大语言模型中的联合令牌提交
Don't Commit Alone: Joint Token Commitment in Diffusion Language Models
arXiv 2607.04469 · 2026-08-26搜索的新形态：对话式人工智能如何重新构建信息获取
The New Shape of Search: How Conversational AI Recomposes Information Seeking
arXiv 2607.04282 · 2026-08-26用于分类性能评估的统一代数框架
A Unified Algebraic Framework for Classification Performance Evaluation
arXiv 2607.04028 · 2026-08-26黑洞视界分支选择的光滑性原理
A Horizon-to-Boundary Dictionary Linking Smooth Horizon Continuation, Pole-Skipping, and \(SL(2,\mathbb R)\) Lowest-Weight Structure
arXiv 2607.03800 · 2026-08-26$S^{1}$上$S^{1}$-丛上纤维映射的同伦极小周期
Homotopy minimal periods for fiber maps on circle bundles over circle
arXiv 2607.02769 · 2026-08-26函数调用中结构化输出增益的归因：接口对齐与过程转移
Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural Transfer
arXiv 2607.02595 · 2026-08-26LIB-TRAP: 标准单元库硬件木马风险评估与防范
LIB-TRAP: Standard Cell Library Hardware Trojan Risk Assessment and Prevention
arXiv 2607.01526 · 2026-08-26RusFinChain：面向金融领域可验证思维链推理的俄语基准与模糊对齐评估
RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation
arXiv 2607.01388 · 2026-08-26Wheeler确定化问题的更紧界
Tighter Bounds for Wheeler Determinization
arXiv 2607.01007 · 2026-08-26昼夜变暖与印度结构转型
Night and Day: Diurnal Warming and Structural Change
arXiv 2607.00279 · 2026-08-26ReWorld：具有长程记忆的交互式世界模型
ReWorld: An Interactive World Model with Long-Horizon Memory
arXiv 2608.23565 · 2026-08-25SWE Refactor Bench：编码智能体能完成长周期的全仓库栈迁移吗？
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
arXiv 2608.23564 · 2026-08-25EG-ARSA：适用于低资源场景的基于专家知识的开放视觉道路安全审计模型
EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings
arXiv 2608.23563 · 2026-08-25Kitaev自旋液体隧穿谱中通量诱导的阿哈罗诺夫-玻姆振荡
Flux-induced Aharonov-Bohm Oscillation in the Tunneling Spectroscopy of Kitaev Spin Liquids
arXiv 2608.23561 · 2026-08-25原子电子约瑟夫森项链中的旋量凝聚体持续电流
Spinor condensate persistent currents in an atomtronic Josephson necklace
arXiv 2608.23560 · 2026-08-25COLIBRE模拟中红移z≳10的詹姆斯·韦布空间望远镜（JWST）星系的后代
The descendants of $z \gtrsim 10$ JWST galaxies in the COLIBRE simulations
arXiv 2608.23558 · 2026-08-25四维中的四元数厄米带几何：在$S^4$上的实现与在$T^4$上的阻碍
Quaternionic Hermitian Band Geometry in Four Dimensions: Realization on $S^4$ and Obstruction on $T^4$
arXiv 2608.23556 · 2026-08-25可证明的均匀与重掩蔽离散扩散模型的自适应采样
Provably adaptive sampling with uniform and remasking discrete diffusion models
arXiv 2608.23554 · 2026-08-25Prime Agent：一种自改进的RLM管控框架
Prime Agent: A Self-Improving RLM Harness
arXiv 2608.23552 · 2026-08-25ConvergeFlow：可收敛至词元嵌入的语言流模型
ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings
arXiv 2608.23551 · 2026-08-25当“不要”并非“拒绝”：CLAUDE.md中的安全规则与内置控制
When "Do Not" Is Not Deny: Security Rules in CLAUDE.md vs Built-In Controls
arXiv 2608.23550 · 2026-08-25FixAnything：基于视频生成先验的3D一致性渲染优化
FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
arXiv 2608.23549 · 2026-08-25为早期演化探测器做准备：类地大气中耀斑温度对臭氧柱深度的影响
Preparing for the Early eVolution Explorer: The Impact of Flare Temperature on Ozone Column Depth in Earth-Like Atmospheres
arXiv 2608.23548 · 2026-08-25训练时数据污染下工业控制系统异常检测模型的鲁棒性
Robustness of Anomaly Detection Models for Industrial Control Systems under Training-Time Data Contamination
arXiv 2608.23547 · 2026-08-25用于耗散型时变偏微分方程的惯性流形神经算子
Inertial Manifold Neural Operator for Dissipative Time-Dependent Partial Differential Equations
arXiv 2608.23546 · 2026-08-25二维整数格上的欧拉行走者具有范围指数2/3
Eulerian walkers on $\mathbb{Z}^2$ have range exponent $2/3$
arXiv 2608.23545 · 2026-08-25格点立方体的无和子集的数量
The number of sum-free subsets of lattice cubes
arXiv 2608.23544 · 2026-08-25AI辅助如何影响人类技能发展：一项基于逻辑谜题学习的研究
How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles
arXiv 2608.23543 · 2026-08-25图中子路径的数量与平均长度
The number and average length of subpaths in graphs
arXiv 2608.23542 · 2026-08-25交互税：当多智能体团队中的沟通消除多样性时
The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
arXiv 2608.23541 · 2026-08-25带乘性噪声的随机Allen-Cahn方程的随机流
A Stochastic Flow for the Stochastic Allen-Cahn Equation with Multiplicative Noise
arXiv 2608.23540 · 2026-08-25模N整数环的压缩零因子图的盒维数
The boxicity of the compressed zero divisor graph of the ring of integers modulo N
arXiv 2608.23539 · 2026-08-25引力湍流盘中的尘埃捕获、碰撞速度与速度弥散
Dust trapping, collisional velocity and velocity dispersion in gravito-turbulent discs
arXiv 2608.23537 · 2026-08-25
