2026-07论文中文摘要
使用局部边界条件耦合局部和非局部问题
Coupling of Local and Nonlocal Problems Using Local Boundary Conditions
arXiv 2607.22672 · 2026-07-28AIR-BENCH Live：基础模型不断演进的安全基准测试
AIR-BENCH Live: An Evolving Safety Benchmark for Foundation Models
arXiv 2607.22671 · 2026-07-28时间尺度上反向Callebaut、Rogers Hölder和Cauchy Schwarz不等式的核型分数扩展
Kernel-Type Fractional Extensions of Reverse Callebaut, Rogers Hölder and Cauchy Schwarz Inequalities on Time Scales
arXiv 2607.22670 · 2026-07-28关于二次单一生成半环的双-UF正猜想及相关进展
The Bi-UF Positive Conjecture for quadratic monogenic semirings and related progress
arXiv 2607.22669 · 2026-07-28遗忘：推荐系统中的高效遗忘
Obliviate: Efficient Unlearning in Recommender Systems
arXiv 2607.22665 · 2026-07-28关于最优多项式逼近常数的代数复杂性
On the Algebraic Complexity of Optimal Polynomial Approximation Constants
arXiv 2607.22664 · 2026-07-28CuraWeb：网络规模预训练数据的质量、冗余性和多样性联合优化
CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data
arXiv 2607.22662 · 2026-07-28TRE：用于扩散语言模型的无训练幻觉检测
TRE: Training-Free Hallucination Detection for Diffusion Language Models
arXiv 2607.22661 · 2026-07-28通过随机控制和正倒向随机微分方程对扩散模型进行广义微调
Generalized Fine-Tuning of Diffusion Models via Stochastic Control and FBSDEs
arXiv 2607.22660 · 2026-07-28分数阶积分和微分方程的变分公式
Variational Formulations for Fractional Integral and Differential Equations
arXiv 2607.22659 · 2026-07-28StanceBench：一个基于音频大语言模型的语音人际立场评估基准
StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech
arXiv 2607.22658 · 2026-07-28你在跟我说话吗？：电影剧本中性别化的说话者-听话者模式的网络分析
You Talkin to Me?: A Network Analysis of Gendered Speaker-Addressee Patterns in Film Screenplays
arXiv 2607.22656 · 2026-07-28EventOD：通过大语言模型引导的语义调制实现事件感知的OD流生成
EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation
arXiv 2607.22655 · 2026-07-28MINT-V2X：用于预测资源管理的移动集成网络轨迹数据集
MINT-V2X: A Mobility-Integrated Network Trajectory Dataset for Predictive Resource Management
arXiv 2607.22654 · 2026-07-28语言模型会收敛到自身吗？递归自精炼作为文本松弛
Do Language Models Converge to Themselves? Recursive Self-Refinement as Textual Relaxation
arXiv 2607.22653 · 2026-07-28KG2Code：通过可执行代码连接知识图谱与大语言模型以进行问答
KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering
arXiv 2607.22652 · 2026-07-28ARdena：实时大语言模型智能体的场景驱动控制
ARdena: Scenario-driven control of real-time LLM agents
arXiv 2607.22651 · 2026-07-28锥形平均映射的模及其在两个子空间夹角中的应用
Modulus of conically averaged mappings and its applications to angles between two subspaces
arXiv 2607.22650 · 2026-07-28STAIF：一种用于复杂指令跟随的逐阶段优化方法
STAIF: A Stage-wise Optimization for Complex Instruction Following
arXiv 2607.22649 · 2026-07-28PTStore（前缀张量存储）：用于高吞吐量推理服务的分布式前缀缓存与复制
PTStore (Prefix Tensor Store): Distributed Prefix Caching and Replication for High Throughput Inference Serving
arXiv 2607.22648 · 2026-07-28二阶的上下近似。二阶穷竭器
Upper and lower approximations of the second order. Exhausters of the second order
arXiv 2607.22647 · 2026-07-28从预训练语言模型中提取算法：以隐马尔可夫模型为例
Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models
arXiv 2607.22646 · 2026-07-28关于‘奥格雷迪六维流形上素数阶非辛自同构’的勘误
Corrigendum to "Nonsymplectic automorphisms of prime order on O'Grady's sixfolds"
arXiv 2607.22645 · 2026-07-28DocHRL：用于成本优化文档分类的分层强化学习框架
DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification
arXiv 2607.22644 · 2026-07-28检索前先思考：多模态检索增强生成的智能体规划
Reason Before You Retrieve: Agentic Planning for Multi-modal RAG
arXiv 2607.22643 · 2026-07-28CRAFT：学习模式，执行计划
CRAFT: Learn the Schema, Execute the Plan
arXiv 2607.22642 · 2026-07-28自动聚类、自动主题建模、自动趋势分析：用于预测新兴趋势的完整自动化机器学习管道
AutoCluster, AutoTopicModeling, AutoTrendAnalysis: A Complete AutoML Pipeline for Predicting Emerging Trends
arXiv 2607.22641 · 2026-07-28在“我们所有人”研究项目中，人工智能辅助的环境和社会心理因素对主观认知困难的因果推断及中介分析
AI-Assisted Causal Inference and Mediation Analyses of Environmental and Psychosocial Determinants of Subjective Cognitive Difficulties in the All of Us Research Program
arXiv 2607.22640 · 2026-07-28TRACE：用于企业语言模型中知识保留参数化工具检索的业务规则基础推理课程
TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs
arXiv 2607.22639 · 2026-07-28基于总量控制与交易机制的污染减排均值场模型
Mean-field model for pollution abatement via cap and trade mechanism
arXiv 2607.22638 · 2026-07-28通过信道条件参数生成实现CSI模型的快速跨场景自适应
Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation
arXiv 2607.22637 · 2026-07-28CallBench：电话助手双目标协调基准测试
CallBench: A Benchmark for Dual-Goal Coordination in Phone Call Assistants
arXiv 2607.22635 · 2026-07-28PRESTO：用于扩散推测解码的前缀对齐树草稿生成
PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding
arXiv 2607.22634 · 2026-07-28VlogReward：学习用于Vlog编辑的多维评估
VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing
arXiv 2607.22632 · 2026-07-28费米-伯恩-因费尔德电动力学：一种具有物理规范的非线性理论
Fermi--Born--Infeld electrodynamics: a nonlinear theory with physical gauge
arXiv 2607.22631 · 2026-07-28为能源系统优化对不确定输入参数的相关结构进行建模
Modelling the Correlation Structure of Uncertain Input Parameters for Energy System Optimization
arXiv 2607.22630 · 2026-07-28网络分析揭示了具有不同饲料供应能力和土地需求的农业食品氮系统中的相变
Network analysis reveals phase transitions in agro-food nitrogen systems with contrasting feeding capacity and land requirement
arXiv 2607.22628 · 2026-07-28TokenMem：为冻结的语言模型进行忠实的知识注入
TokenMem: Faithful Knowledge Injection for Frozen LLMs
arXiv 2607.22625 · 2026-07-28CHS-SQL：一种基于置信度引导启发式搜索模式链接过程的文本到SQL方法
CHS-SQL: A Text-to-SQL approach based on Confidence-Guided Heuristic Search Schema Linking process
arXiv 2607.22624 · 2026-07-28增强电力-计算相互依存系统应对突发事件的恢复能力
Resilience Enhancement of Electricity-Computing Interdependency System against Contingency
arXiv 2607.22623 · 2026-07-28通过监督微调（SFT）和直接偏好优化（DPO）学习何时对文本到SQL进行推理
Learning When to Reason for Text-to-SQL via SFT and DPO
arXiv 2607.22622 · 2026-07-28Opti-Q：一种用于多语言模型问题规划的基于约束的优化框架
Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning
arXiv 2607.22621 · 2026-07-28SS - RS - GD不等式的一个解答
A Resolution of the SS--RS--GD Inequalities
arXiv 2607.22620 · 2026-07-28如何管控GPU：国际人工智能协议的验证与执行机制分类法
How to Catch a GPU: A Taxonomy of Verification and Enforcement Mechanisms for International AI Agreements
arXiv 2607.22619 · 2026-07-28平衡比特与水滴：数据中心的压力调整型水管理
Balancing Bits and Drops: Stress-Adjusted Water Management for Data Centers
arXiv 2607.22617 · 2026-07-28基于线性α-截集区间的简约模糊最佳-最差方法及其在仓库选址中的应用
A Linear alpha-cut intervals based Parsimonious Fuzzy Best-Worst Method with an Application to Warehouse Location Selection
arXiv 2607.22616 · 2026-07-28掩码自动编码器从静息态神经数据中学习与感知相关的表示
Masked Autoencoders Learn Perception-Relevant Representations from Resting State Neural Data
arXiv 2607.22615 · 2026-07-28通过文化和政治记忆振兴城市公共空间：一种利用大语言模型和增强现实的技术方法
Revitalizing Public Urban Places through Cultural and Political Memory: A Technological Approach with LLMs and Augmented Reality
arXiv 2607.22613 · 2026-07-28商树算法：具有有界符号深度和跨子树抵消的延迟除法计算
Quotient Tree Arithmetic: Deferred-Division Computation with Bounded Symbolic Depth and Cross-Subtree Cancellation
arXiv 2607.22612 · 2026-07-28关键基础设施中智能体人工智能系统的去中心化粒度访问控制
Decentralized Granular Access Control for Agentic AI Systems in Critical Infrastructure
arXiv 2607.22611 · 2026-07-28
