2026-09论文中文摘要
CP-WSP：面向可配置多约束员工排班的声明式CP-SAT框架
CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling
arXiv 2607.05177 · 2026-09-01评价的是宣传话术，而非产品本身：用户对大语言模型的评估更多反映期望而非性能
Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance
arXiv 2607.05113 · 2026-09-01多分量短脉冲方程的可积全离散化
Integrable full discretization of the multi-component short pulse equation
arXiv 2607.04756 · 2026-09-01具有从下方有界的修正Ricci曲率的完备流形上Witten拉普拉斯算子和加权p-拉普拉斯算子的特征值比较定理
Eigenvalue comparison theorems for the Witten-Laplacian and the weighted $p$-Laplacian on complete manifolds with a modified Ricci curvature bounded from below
arXiv 2607.04588 · 2026-09-01教师的少量步骤作用显著：智能体训练后基于策略的数据增强的成本效益
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
arXiv 2607.04574 · 2026-09-01基于自旋涨落的非微扰多体理论的铜酸盐d波超导性
Cuprate d-wave superconductivity based on Non perturbative many body theory for spin fluctuation
arXiv 2607.04168 · 2026-09-01不假设酉可观测量的两量子比特最大纠缠态的稳健自测试
Robust self-test of the maximally entangled state of two-qubits without assuming unitary observables
arXiv 2607.04035 · 2026-09-01我们能低到什么程度？超新星亚型分类的最低光谱要求
How Low Can We Go? Minimum Spectroscopic Requirements For Supernova Subtype Classification
arXiv 2607.03532 · 2026-09-01极值集论中交叉相交问题的统一方法及其在希尔顿 - 米尔纳型定理和稳定性中的应用
A unified approach to cross-intersection problems with applications to Hilton--Milner type theorems and stability
arXiv 2607.03315 · 2026-09-01利用大型强子对撞机和低能实验探测一个146 GeV的轻子味违反标量粒子
Probing a 146 GeV cLFV scalar using the LHC and low-energy experiments
arXiv 2607.03249 · 2026-09-01使用Incognita评估基于社会分布式任务环境中行动的生成智能体
Where Knowledge and Authority Sit Changes What an Agent Benchmark Can Resolve
arXiv 2607.02975 · 2026-09-01标准条件上下文学习：评估视觉语言模型中的标准转移适应性
Criterion-Conditional In-Context Learning: Evaluating Criterion-Shift Adaptation in Vision-Language Models
arXiv 2607.02575 · 2026-09-01用于稀疏视图神经重建的可靠性感知单目深度监督
Reliability-Aware Monocular Depth Supervision for Sparse-View Neural Reconstruction
arXiv 2607.02554 · 2026-09-01LLM人格的双重性质：聚合倾向与框架依赖的几何结构
Cultural Bias Without a Cultural Self:A Disassociation Study of LLM's Persona and Bias
arXiv 2607.02368 · 2026-09-01DisciplineGen-1M：用于多学科视觉生成与编辑的大规模数据集
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
arXiv 2607.02290 · 2026-09-01从Bloch到Néel：FePd薄膜中依赖各向异性的畴壁特征
From Bloch to Néel: Anisotropy-dependent Domain-Wall Character in FePd Thin Films
arXiv 2607.02256 · 2026-09-01贝叶斯稀疏低秩自适应用于大语言模型不确定性估计
Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation
arXiv 2607.02182 · 2026-09-01场景条件PINN-GNN用于多径射频地图：跨场景生成与场景内补全
Scene-Conditioned PINN-GNN for Multipath RF Maps: Cross-Scene Generation and In-Scene Completion
arXiv 2607.01777 · 2026-09-01一个演示足以实现真实世界机器人强化学习
One Demonstration Is Enough for Real-World Robotic Reinforcement Learning
arXiv 2607.01651 · 2026-09-01Vitriflow: 通过熔淬模拟获得校准的非晶结构系综
Vitriflow: calibrated amorphous structure ensembles from melt-quench simulation
arXiv 2607.01407 · 2026-09-01双轨猫码中的偏压保持门与量子纠错
Bias-Preserving Gates and Quantum Error Correction With Dual-Rail Cat Codes
arXiv 2607.00786 · 2026-09-01多输入多输出相位调制信道中某种收发器架构的性能评估
Performance Evaluation of A Certain Transceiver Architecture for Multiple-Input Multiple-Output Phase-Modulated Channels
arXiv 2607.00356 · 2026-09-01Mnemosyne: 用于验证和修复AI生成工作流的代理事务处理
Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows
arXiv 2607.00269 · 2026-09-01面向具身智能的记忆原生非地面网络
Memory-Native Non-Terrestrial Networks for Embodied Intelligence
arXiv 2607.00029 · 2026-09-01
