2026-08论文中文摘要
从关系型和属性图数据到大语言模型
From Relational and Property Graph Data to Large Language Models
arXiv 2608.12407 · 2026-08-14量子自旋连接泡沫在太阳系、星系及宇宙中的效应
Effects of Quantum Spin-Connection Foam in the Solar System, Galaxies, and the Universe
arXiv 2608.12404 · 2026-08-14跨不同特征集的黑盒知识迁移
Black-Box Knowledge Transfer across Distinct Feature Sets
arXiv 2608.12403 · 2026-08-14分数阶微分方程中的“相变”
"Phase Transition" in fractional differential equations
arXiv 2608.12402 · 2026-08-14二叉树高度的热带代数
The Tropical Algebra of Binary-Tree Height
arXiv 2608.12401 · 2026-08-14素数作为概率测度谱的条件算术障碍
A conditional arithmetic obstruction to the prime numbers as a spectrum of a probability measure
arXiv 2608.12400 · 2026-08-14雅可比椭圆函数的广义加法定理
Generalized Addition Theorems for the Jacobi Elliptic Functions
arXiv 2608.12399 · 2026-08-14面向多模态认知的分层能量基模型
A Hierarchical Energy-Based Model for Multimodal Cognition
arXiv 2608.12398 · 2026-08-14关于混合幂的华林-哥德巴赫问题
On Waring--Goldbach problem with mixed powers
arXiv 2608.12397 · 2026-08-14芝诺的恶魔与基于Transformer的人类行为计算模型的领域普适性否定
Zenons Demon and the Denial of Domain-Generality for Transformer-Based Computational Models of Human Behavior
arXiv 2608.12396 · 2026-08-14研究助手：阿斯利康的研发智能体系统
Research Assistant: AstraZeneca's Agentic System for R&D
arXiv 2608.12395 · 2026-08-14VR-IPS：用于光敏感性诊断的虚拟现实光刺激工具
VR-IPS: Virtual Reality Tool for Photic Stimulation in Photosensitive Diagnosis
arXiv 2608.12394 · 2026-08-14元认知技能学习：一种计算解释
Metacognitive Skill Learning: A Computational Account
arXiv 2608.12393 · 2026-08-14跨维推断中的学习型提议在平衡态时最优，而非在构建过程中
Learned proposals in trans-dimensional inference are optimal at equilibrium, not during assembly
arXiv 2608.12392 · 2026-08-14面向大语言模型复杂图推理的统一多维度基准
Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models
arXiv 2608.12391 · 2026-08-14通过元LoRA学习适应跨领域偏好以实现大语言模型个性化
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
arXiv 2608.12389 · 2026-08-14皮层方向选择性的贝叶斯-马尔可夫神经形态模型：计算重实现与定量模拟研究
A Bayes-Markov Neuromorphic Model of Cortical Orientation Selectivity: A Computational Re-implementation and Quantitative Simulation Study
arXiv 2608.12388 · 2026-08-14查询时机在大型语言模型（LLMs）与人类之间产生相反的位置偏差
Query Timing Produces Opposite Positional Biases Between LLMs and Humans
arXiv 2608.12387 · 2026-08-14[18F]FDG转运与代谢的微观计算模拟确定了室分析的有效范围
A microscopic computational simulation of [18F]FDG transport and metabolism identifies valid regimes for compartmental analysis
arXiv 2608.12386 · 2026-08-14基于函数$ϕ$组织形式零点产生的牛顿-拉夫逊-辛普森法的多点变体
Multi-point variants of the Newton-Raphson-Simpson method arising from organizing a formal zero according to a function $ϕ$
arXiv 2608.12384 · 2026-08-14混杂暗物质的奇异夸克星中的微观相互作用与纯引力耦合：单流体与双流体的比较
Microscopic Interaction versus Purely Gravitational Coupling in Strange Quark Stars Admixed with Dark Matter: A One-Fluid and Two-Fluid Comparison
arXiv 2608.12383 · 2026-08-14营养结构预测脑网络模型中的癫痫发作传播
Trophic structure predicts seizure propagation in brain network models
arXiv 2608.12382 · 2026-08-14带反应项的一维退化扩散方程解的正则性
Regularity of Solutions to One-Dimensional Degenerate Diffusion Equations with Reactions
arXiv 2608.12381 · 2026-08-14旋转中子星上的马格努斯山
Magnus mountains on spinning neutron stars
arXiv 2608.12378 · 2026-08-14从观察到干预：大脑与大型语言模型中的记忆
From Observation to Intervention: Memory in Brains and Large Language Models
arXiv 2608.12377 · 2026-08-14用于Dirichlet热方程的边界校正Li--Yau估计的热核期望方法
A Heat Kernel Expectation Approach to Boundary-Corrected Li--Yau Estimates for the Dirichlet Heat Equation
arXiv 2608.12376 · 2026-08-14管道指称设计：零成本的构造正确性数据管道
Pipeline Denotational Design: Correct-by-Construction Data Pipelines at Zero Cost
arXiv 2608.12375 · 2026-08-14你在跟我讲逻辑吗？评估语言模型的三段论推理能力
Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities
arXiv 2608.12374 · 2026-08-14不想让你的大语言模型（LLM）推荐核打击？试试用日语提问
Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese
arXiv 2608.12373 · 2026-08-14立场：我们需要实用的AI对齐方法来镜像人类推理
Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning
arXiv 2608.12372 · 2026-08-14面向移动边缘计算中流处理的、基于大语言模型辅助合同网协商的多智能体调度
Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
arXiv 2608.12371 · 2026-08-14当我们谈论信息图表时，我们指的是什么？
What Do We Mean When We Talk About Infographics?
arXiv 2608.12370 · 2026-08-14各恰当相位中的随机非线性波
Stochastic Nonlinear Waves in all the Right Phases
arXiv 2608.12369 · 2026-08-14一致性并非对齐：人类与大语言模型（LLM）伦理判断中的道德依据分歧
Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
arXiv 2608.12368 · 2026-08-14非对称金融数据集的生命周期感知归档：一项生产研究
Lifecycle-Aware Archival for Asymmetric Financial Datasets: A Production Study
arXiv 2608.12367 · 2026-08-14六阶Boussinesq方程的空间衰减与非线性光滑性
Spatial decay and nonlinear smoothing of the sixth-order Boussinesq equation
arXiv 2608.12366 · 2026-08-14欧盟碳排放交易体系面临冲击？碳价抑制对电力部门脱碳的影响
EU-ETS under attack? The impact of carbon price suppression on the decarbonization of the power sector
arXiv 2608.12363 · 2026-08-14面向策略的反馈：促进机器学习教育中的系统性问题解决能力
Strategy-Oriented Feedback for Fostering Systematic Problem-Solving in Machine Learning Education
arXiv 2608.12362 · 2026-08-14新术语，新毒性：基于共识的新词毒性检测——通过搜索增强型大语言模型（LLMs）
New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
arXiv 2608.12361 · 2026-08-14监管批准并不足够：FDA clearance医疗设备中可信赖AI报告的缺口
Regulatory Approval Is Not Enough: Gaps in Trustworthy AI Reporting in FDA-Cleared Medical Devices
arXiv 2608.12360 · 2026-08-14我们能信任超市中的智能体吗？从产品图像推断糖含量
Can We Trust AI Agents in the Supermarket? Sugar Content Inference from Product Images
arXiv 2608.12359 · 2026-08-14交互就绪：构建和评估人类角色AI智能体的框架
Interaction Readiness: A Framework for Building and Evaluating AI Agents in Human Roles
arXiv 2608.12358 · 2026-08-14通过交流绘画来表达：创意支持研究本身即是创意过程
DrawTalking It Out: Creativity-Support Research as Creative Process Itself
arXiv 2608.12357 · 2026-08-14在项目组合规模下衡量课程与劳动力市场的匹配度
Measuring Curriculum-Labor Market Alignment at the Scale of a Program Portfolio
arXiv 2608.12356 · 2026-08-14AI编码智能体研究中缺失了人类
Humans are Missing from AI Coding Agent Research
arXiv 2608.12355 · 2026-08-14SCALE-Sim EVA：可扩展、可可视化且可适配的加速器模拟框架的设计原则
SCALE-Sim EVA: Design Principles for an Extensible, Visualizable, and Adaptable Accelerator Simulation Framework
arXiv 2608.12354 · 2026-08-14可见性不对称：供应商注意力如何决定哪些教育技术故障成为产品可见的
Visibility Asymmetry: How Vendor Attention Shapes Which EdTech Breakdowns Become Product-Visible
arXiv 2608.12353 · 2026-08-14为何AI治理框架难以被采用：对NIST AI RMF的基于角色的压力测试
Why AI Governance Frameworks Are Hard to Adopt: A Role-Based Stress Test of the NIST AI RMF
arXiv 2608.12352 · 2026-08-14生成式人工智能（GenAI）时代的评估设计：用于测试学生AI素养、学习成果与反思的X1-X2-X3评估模式
Assessment Design in the GenAI Era: The X1-X2-X3 Assessment Pattern for Testing Students' AI Literacy, Learning Outcomes, and Reflection
arXiv 2608.12351 · 2026-08-14从原始人到专家分析师：可变大语言模型任务的能耗
From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks
arXiv 2608.12350 · 2026-08-14
