2026-07论文中文摘要
诊断前先询问：Safe-Psych，一种用于精神病学领域大语言模型的顺序评估基准
Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry
arXiv 2607.13036 · 2026-07-16FixItFlow：从云事件中自动生成故障排除指南
FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents
arXiv 2607.13035 · 2026-07-16DermDepth：迈向用于皮肤病学的单目度量尺度3D重建模型
DermDepth: Toward Monocular Metric Scale 3D Reconstruction Models for Dermatology
arXiv 2607.13010 · 2026-07-16频谱并不够：上下文何时有助于时间序列预测
The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting
arXiv 2607.13006 · 2026-07-16X-Lens：使用异构相机进行实时度量深度估计
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
arXiv 2607.12993 · 2026-07-16用于公平高效恶性肿瘤分类的可控多样皮肤病图像生成
Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification
arXiv 2607.12987 · 2026-07-16稳健性的错觉：聚合准确率掩盖了与任务无关的上下文下的预测翻转
The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context
arXiv 2607.12963 · 2026-07-16用于参数化动作马尔可夫决策过程的知识与梯度引导强化学习
Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
arXiv 2607.12924 · 2026-07-16建立光学湍流预测的基线模型性能
Establishing baseline model performances for optical turbulence forecasting
arXiv 2607.12900 · 2026-07-16代码等价性综述：现状与开放问题
A Survey on Code Equivalence: The State-of-the-Art and Open Questions
arXiv 2607.12870 · 2026-07-16多体系统中用于涌现二能级子空间的与时间无关的反绝热驱动
Time-independent counterdiabatic driving for emergent two-level subspaces in many-body systems
arXiv 2607.12848 · 2026-07-16有限维系统中动态量子相变的热抑制：一个准厄米框架
Thermal Suppression of Dynamical Quantum Phase Transitions in Finite-Dimensional Systems A Quasi-Hermitian Framework
arXiv 2607.12838 · 2026-07-16打破似曾相识：通过视觉语言推理对视觉场所识别进行独立审计
Breaking Déjà Vu: Independent Auditing of Visual Place Recognition through Vision-Language Reasoning
arXiv 2607.12818 · 2026-07-16用于电磁散射的对称信息深度学习
Symmetry-Informed Deep Learning for Electromagnetic Scattering
arXiv 2607.12810 · 2026-07-16ExtraGS：通过扩散引导的3D高斯点渲染增强内窥镜视图外推
ExtraGS: Enhancing Endoscopic View Extrapolation via Diffusion-Guided 3D Gaussian Splatting
arXiv 2607.12785 · 2026-07-16由虫洞制备的量子态：与Bunch-Davies的长波长偏差
Quantum States Prepared by Wormholes: Long-Wavelength Deviations from Bunch-Davies
arXiv 2607.12772 · 2026-07-16有理正规曲线上的循环射影轨道与MDS码
Cyclic Projective Orbits on Rational Normal Curves and MDS Codes
arXiv 2607.12761 · 2026-07-16Hallo4D：用于一致时空生成的多模态幻觉缓解
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
arXiv 2607.12752 · 2026-07-16压实压力对用于中温固体氧化物燃料电池的钆掺杂二氧化铈电解质阻抗的影响
Influence of compaction pressure on the impedance of Gadolinium Doped Ceria electrolytes for IT-SOFCs
arXiv 2607.12719 · 2026-07-16单组分和双组分玻色-哈伯德模型基态和温度特性的标准基算子方法
Standard basis operator method for ground-state and temperature properties of single and two-component Bose-Hubbard model
arXiv 2607.12718 · 2026-07-16AutoSIFT：用于可控语音生成的自动风格筛选与任意风格填充
AutoSIFT: Automatic Style Sifting for Controllable Speech Generation with Arbitrary Style Infilling
arXiv 2607.12706 · 2026-07-16KnowAct-GUIClaw：深度理解、完美执行，具有自我进化记忆和技能的个人GUI助手
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
arXiv 2607.12625 · 2026-07-16三百项目：低气体分数星系团的性质及其环境
The Three Hundred project: Low Gas Fraction Galaxy Clusters properties and their environment
arXiv 2607.12607 · 2026-07-16完全二叉树和蜘蛛树优美标号中的交替极值
Alternating Extremes in Graceful Labelings of Full Binary Trees and Spider Trees
arXiv 2607.12597 · 2026-07-16多晶体中马氏体微观结构的相容性
Compatibility of Martensitic Microstructures in Polycrystals
arXiv 2607.12572 · 2026-07-16注意差距：LeWorldModel中分层规划的前景与陷阱
Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel
arXiv 2607.12547 · 2026-07-16使用自主人工智能驱动优化的脑电图癫痫检测降维方法比较
Comparison of Dimension Reduction Methods for EEG Seizure Detection Using Autonomous AI-Driven Optimization
arXiv 2607.12546 · 2026-07-16正交结构铋单层中局域场和偶极-偶极相互作用对偶极矩自发有序化的影响
Effect of the local field and dipole-dipole interaction on the spontaneous ordering of dipole moments in bismuth monolayers with an orthorhombic structure
arXiv 2607.12542 · 2026-07-16通过搜索内核协同设计实现可实现的N:M稀疏Transformer推理
Realizable N:M Sparse Transformer Inference via Search-Kernel Co-Design
arXiv 2607.12505 · 2026-07-16DynTrace：用于多模态大语言模型中4D时空推理的动态对象证据跟踪
DynTrace: Tracking Dynamic Object Evidence for 4D Spatio-Temporal Reasoning in MLLMs
arXiv 2607.12503 · 2026-07-16ZipL-Dialog：通过潜在流匹配实现内存高效的长格式语音对话合成
ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching
arXiv 2607.12496 · 2026-07-16伊藤-温策尔公式与迪皮雷随机偏微分方程
Ito-Wentzell Formula and Dupire Stochastic PDE
arXiv 2607.12479 · 2026-07-16自我在空间中：无人机具身智能中的自我意识与空间认知基准测试
Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence
arXiv 2607.12477 · 2026-07-16从观察到洞察：机制世界模型与自主发现探索
From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery
arXiv 2607.12474 · 2026-07-16自动驾驶车辆交互的自动测试
Automatic Testing of Interacting Autonomous Vehicles
arXiv 2607.12452 · 2026-07-16关于紧致度量图的 p - 扭转刚度：一个精确的科勒 - 乔宾不等式
On the p-torsional rigidity of compact metric graphs: a sharp Kohler--Jobin inequality
arXiv 2607.12333 · 2026-07-16Mystra：通过影子虚拟机进行声明式动态污点分析
Mystra: Declarative Dynamic Taint Analysis via Shadow Virtual Machine
arXiv 2607.12308 · 2026-07-16$(C^{\vee},C)$型稳定极限双仿射赫克代数与稳定极限科恩温德多项式
Stable Limit DAHA of type $(C^{\vee},C)$ and Stable Limit Koornwinder Polynomials
arXiv 2607.12276 · 2026-07-16金融研究基准II：一个具有共识衍生黄金标准的深度研究基准，用于区分财务报告质量
FinResearchBench II: A Deep Research Benchmark with Consensus-Derived Gold Rubrics for Distinguishing Financial Report Quality
arXiv 2607.12252 · 2026-07-16单位圆上的特征子群
Characterized subgroups on the unit circle
arXiv 2607.12192 · 2026-07-16极性纤锌矿型MnTe的相控外延与各向异性反铁磁性
Phase-Controlled Epitaxy and Anisotropic Antiferromagnetism of Polar Wurtzite MnTe
arXiv 2607.12191 · 2026-07-16从互补超声表征中学习用于肝病分类
Learning from Complementary Ultrasound Representations for Liver Disease Classification
arXiv 2607.12062 · 2026-07-16承保智能体经济：人工智能保险堆栈蓝图
Underwriting the Agent Economy: The Blueprint for an AI Insurance Stack
arXiv 2607.11999 · 2026-07-16我们合并的模型正确吗？专家训练时长对大语言模型模型合并的影响
Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs
arXiv 2607.11997 · 2026-07-16VQCSim：何时编译一次的态矢量模拟优于通用量子框架？
VQCSim: When Does Compile-Once Statevector Simulation Beat Generic Quantum Frameworks?
arXiv 2607.11985 · 2026-07-16可移除缺陷：故意不足的经济学与局限性
Removable Defects: The Economics and Limits of Deliberate Deficiency
arXiv 2607.11983 · 2026-07-16优化并非你所需的全部
Optimization Is Not All You Need
arXiv 2607.11977 · 2026-07-16基于风险重写的广义无分布半监督学习
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
arXiv 2607.11947 · 2026-07-16一个拉马努金 - 佩尔椭圆K3曲面与原始的五立方近 misses
A Ramanujan Pell Elliptic K3 Surface and Primitive Five-Cube Near Misses
arXiv 2607.11925 · 2026-07-16AgentSociety 2：用于可执行社会科学的集成研究环境
AgentSociety 2: An Integrated Research Environment for Executable Social Science
arXiv 2607.11895 · 2026-07-16
