2026-07论文中文摘要
RENEW：迈向从偏好中学习世界模型并修复模型利用问题
RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences
arXiv 2607.14180 · 2026-07-17OvAi Focus：基于人工智能的妇科超声中功能性卵巢和附件包块的多类别分割
OvAi Focus: AI-based Multi-class Segmentation of Functional Ovaries and Adnexal Masses in Gynecological Ultrasound
arXiv 2607.14179 · 2026-07-17具有不确定关节刚度的电机位置控制柔性关节机器人的自适应控制
Adaptive Control of Motor-Position-Controlled Flexible Joint Robots with Uncertain Joint Stiffness
arXiv 2607.14177 · 2026-07-17基于带边特征的图同构网络的NR-V2X车辆通信低延迟中继选择
Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features
arXiv 2607.14176 · 2026-07-1710-K报告的哪些部分重要？全文与风险因素情绪的聚合相关价值
How Much of a 10-K Matters? Aggregation-Dependent Value of Full-Text versus Risk-Factor Sentiment
arXiv 2607.14174 · 2026-07-17巴丁-反德西特类黑洞中的新型拓扑子类
Novel topological subclass in Bardeen-AdS-class black holes
arXiv 2607.14173 · 2026-07-17基于太空的人工智能计算的成本与网络限制
The Cost and Network Limits of Space-Based AI Compute
arXiv 2607.14172 · 2026-07-17分支策略优化：沙盒原生语言智能体强化学习
Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
arXiv 2607.14171 · 2026-07-17通过嵌入完美流体暗物质的克尔黑洞中的混沌轨道和强场效应探索量子引力
Probing Quantum Gravity through Chaotic Orbits and Strong-Field Effects in Kerr Black Holes Embedded in Perfect Fluid Dark Matter
arXiv 2607.14170 · 2026-07-17通过等距群嵌入在图上构造紧小波框架
Tight Wavelet Frames on Graphs via Isometric Group Embedding
arXiv 2607.14168 · 2026-07-17结构化反馈改进大语言模型智能体循环中的修复
Structured Feedback Improves Repair in an LLM Agent Loop
arXiv 2607.14167 · 2026-07-17迈向可靠的人工智能辅助模拟设计：用于逐次逼近寄存器型模数转换器生成的模板约束大语言模型智能体
Towards Reliable AI-Assisted Analog Design: Template-Constrained LLM Agents for SAR ADC Generation
arXiv 2607.14165 · 2026-07-17通过空间基因制图构建单细胞生物学的视觉基础模型
A vision foundation model for single-cell biology via spatial gene cartography
arXiv 2607.14163 · 2026-07-17QFireNet：用于从哨兵 - 2 影像中进行野火分割的量子增强 U 型网络
QFireNet: A Quantum-Enhanced U-Net for Wildfire Segmentation from Sentinel-2 Imagery
arXiv 2607.14160 · 2026-07-17MemoHarness：从经验中学习的智能体控制层
MemoHarness: Agent Harnesses That Learn from Experience
arXiv 2607.14159 · 2026-07-17利用多智能体人工智能和MCP服务器编排电网研究
Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers
arXiv 2607.14158 · 2026-07-17多域检索的认证域一致性：具有共形风险保证的无标签逐域污染控制
Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees
arXiv 2607.14157 · 2026-07-17轴子质量最低边界估计的新方法
New approach to the estimation of the lowest boundary of an axion mass
arXiv 2607.14156 · 2026-07-17超越对象验证：多工件代理版本中的关系一致性
Beyond Object Validation: Relational Conformance in Multi-Artifact Agent Releases
arXiv 2607.14155 · 2026-07-17一个用于反弹各向异性宇宙的有效弗里德曼方程
An effective Friedmann equation for a bouncing anisotropic universe
arXiv 2607.14153 · 2026-07-17“信任垃圾”导致对高度歧视性预测模型的不合理支持
"Trust Junk" Leads to Unjustified Support for Highly Discriminatory Predictive Models
arXiv 2607.14152 · 2026-07-17使用量子启发表示的对流-扩散-反应系统的张量网络方法
Tensor Network Methods for Advection-Diffusion-Reaction Systems Using Quantum-Inspired Representations
arXiv 2607.14150 · 2026-07-17通过知识图谱基础增强小型语言模型推理
Enhancing Small Language Models Reasoning through Knowledge Graph Grounding
arXiv 2607.14149 · 2026-07-17ITGPT：一种基于Transformer的用于生成《劲舞革命》和《狂热节拍》谱面的架构
ITGPT: A Transformer Based Architecture for the Generation of Dance Dance Revolution and In the Groove Charts
arXiv 2607.14148 · 2026-07-17上半场打破拒绝：预填充越狱的机制研究
Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak
arXiv 2607.14147 · 2026-07-17通过平面偶极场线圈实现的优化有限β托卡马克-仿星器混合构型
Optimized finite-$β$ tokamak-stellarator hybrid configurations achieved by planar dipole-field coils
arXiv 2607.14146 · 2026-07-17ToolAnchor：锚定反事实上下文以提升智能体工具使用能力
ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability
arXiv 2607.14145 · 2026-07-17托马斯正电路猜想的平面情形
The Planar Case of Thomas Positive Circuits Conjecture
arXiv 2607.14143 · 2026-07-17用于具有修正双曲正切分布和优劣高斯混合似然的磁约束等离子体的自动离群值稳健贝叶斯分布拟合
Automated Outlier-Robust Bayesian Profile Fitting for Magnetically Confined Plasmas with Modified Tanh Profiles and Good-and-Bad Gaussian Mixture Likelihoods
arXiv 2607.14142 · 2026-07-17用于运营决策支持的贝叶斯网络的人工AI构建——一种虚拟调查方法
Human AI Construction of Bayesian Networks for Operational Decision Support -- A Virtual Survey Approach
arXiv 2607.14141 · 2026-07-17三位流与圈覆盖。第一部分
Three-Bit Flows and Cycle Covers. Part I
arXiv 2607.14140 · 2026-07-17意志激发：人与机器的操作语义学
Volition Elicitation: Operational Semantics for People and Their Machines
arXiv 2607.14138 · 2026-07-17气体系统中重力诱导的热整流
Gravity-Induced Thermal Rectification in Gaseous Systems
arXiv 2607.14136 · 2026-07-17二维亥姆霍兹方程在半空间中瑞利高频理论的推广：无穷远处辐射条件和一维周期性不均匀边界上狄利克雷条件
Generalization of Rayleigh's high-frequency theory for the 2D Helmholtz equation in a half-space subject to a radiation condition at infinity and a Dirichlet condition on a 1D periodically-uneven boundary
arXiv 2607.14135 · 2026-07-17阿隆 - 弗里德兰德界中的奇圈缺陷
Odd-cycle defects in the Alon-Friedland bound
arXiv 2607.14134 · 2026-07-17关于二维球面共形几何的一个注记
A note on the conformal geometry of the 2-sphere
arXiv 2607.14133 · 2026-07-17齐性空间上拉普拉斯算子的调和变量
Harmonic Variables for Laplace Operators on Homogeneous Spaces
arXiv 2607.14132 · 2026-07-17纪念：温弗里德·布伦斯教授（1946 - 2026）
In Memoriam: Professor Dr. Winfried Bruns (1946--2026)
arXiv 2607.14129 · 2026-07-17通用三次平面曲线多截面的刚性
Rigidity of multisections to the universal cubic plane curve
arXiv 2607.14128 · 2026-07-17利用激光雷达衍生地形智能的卫星地面站选址可解释地理空间人工智能
Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence
arXiv 2607.14127 · 2026-07-17用于闭环1型糖尿病控制的可解释语言模型
Interpretable Language Model for Closed-Loop Type 1 Diabetes Control
arXiv 2607.14126 · 2026-07-17CARPRT：用于黑盒视觉语言模型的类感知零样本提示重加权
CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models
arXiv 2607.14125 · 2026-07-17基于因果模型和层次聚类的公立学校教育绩效分析
Analysis of Public Schools Educational Performance Based on Causal Models and Hierarchical Clustering
arXiv 2607.14124 · 2026-07-17立场：可解释性研究必须优先考虑基础而非临时方法
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
arXiv 2607.14123 · 2026-07-17广义神经分布回归
Generalized Neural Distributional Regression
arXiv 2607.14122 · 2026-07-17通过凝聚数学技术证明相干对偶性
A Proof of Coherent Duality via Techniques from Condensed Mathematics
arXiv 2607.14120 · 2026-07-17用于执行感知大语言模型研究构思的预算子集优化
Budgeted Subset Refinement for Execution-Aware LLM Research Ideation
arXiv 2607.14118 · 2026-07-17ReportMedSAM：通过放射学报告指导分割
ReportMedSAM: Guiding Segmentation Through Radiology Reports
arXiv 2607.14116 · 2026-07-17DialogueVPR：迈向对话式视觉场所识别
DialogueVPR: Towards Conversational Visual Place Recognition
arXiv 2607.14115 · 2026-07-17CoEvoT：用于图语言模型推理的协同进化思维链提示
CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning
arXiv 2607.14114 · 2026-07-17
