2026-07论文中文摘要
RRS-10K：用于罕见遥感图像解释的多任务视觉语言模型基准测试
RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation
arXiv 2607.24810 · 2026-07-29基于物理引导域适应的变工况下飞机压缩机实际剩余使用寿命预测
Towards Real-World RUL Prediction for Aircraft Compressors Under Variable Conditions with Physics-Guided Domain Adaptation
arXiv 2607.24809 · 2026-07-29认知的路径积分模型
A Path Integral Model of Cognition
arXiv 2607.24807 · 2026-07-29在具有不同一致性的多感官反馈下解码错误相关电位
Decoding Error-Related Potentials under Multisensory Feedback with Varying Congruency
arXiv 2607.24806 · 2026-07-29遗忘并非解决之道：序列记忆痕迹编辑中的路径依赖
Forgetting Is Not a Fix: Path Dependence in Sequential Engram Editing
arXiv 2607.24805 · 2026-07-29SciClaimSeekers参加CheckThat! 2026：使用大语言模型重排检索社交媒体声明的科学来源
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
arXiv 2607.24803 · 2026-07-29提示工程对用于安全查询路由的小型语言模型的影响
Influence of Prompt Engineering on Small Language Models for Guarded Query Routing
arXiv 2607.24801 · 2026-07-29当检索前思考有害时：用于自适应知识图谱检索的TraceBound诊断
When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval
arXiv 2607.24800 · 2026-07-29使用开源语言模型进行科学文档理解的多模态混合检索增强生成
Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs
arXiv 2607.24799 · 2026-07-29预测并非记忆：用于持久用户建模的双时间尺度门控配置文件写入
Prediction Is Not Memory: Dual-Timescale Gated Profile Writing for Persistent User Modeling
arXiv 2607.24798 · 2026-07-29当最短路径并非最安全路径时：一种面向老年人友好型行人路线规划的设计科学方法
When Shortest Isn't Safest: A Design Science Approach to Senior-Friendly Pedestrian Routing
arXiv 2607.24795 · 2026-07-29利用记忆进行推理：一种用于免训练长视频理解的时间粒度自适应框架
Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding
arXiv 2607.24794 · 2026-07-29检索而非幻觉将成为基于大语言模型的临床人工智能工具的限制因素
Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools
arXiv 2607.24793 · 2026-07-29能源运营中传统企业资产管理的人工智能辅助知识获取：一个实用检索系统
AI-Assisted Knowledge Access for Legacy Enterprise Asset Management in Energy Operations: A Practical Retrieval System
arXiv 2607.24792 · 2026-07-29从朴素检索增强生成到深度智能检索：用于合规监管的不断演进的上下文工程管道
From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance
arXiv 2607.24791 · 2026-07-29基于GAN的低轨卫星互联网观测数据稳健合成框架
A GAN-Based Framework for Robust Data Synthesis in Satellite Internet Observations
arXiv 2607.24790 · 2026-07-29NEXT：通过视觉语言模型进行推理驱动的视频推荐
NEXT: Reasoning-Driven Video Recommendation via a Vision-Language Model
arXiv 2607.24789 · 2026-07-29GLIDE：用于高效大语言模型推理的引导式分层混合注意力机制
GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference
arXiv 2607.24788 · 2026-07-29DDSNet：用于PCSEL属性预测的双域对称感知网络
DDSNet: Dual-domain Symmetry-aware Network for PCSEL Property Prediction
arXiv 2607.24785 · 2026-07-29关于大语言模型在专业术语方面的应用：语料库的良好替代品？
On the Use of LLMs for Specialised Terminology: A Good Alternative to Corpora?
arXiv 2607.24784 · 2026-07-29领英大规模职位理解的统一语义建模框架
Unified Semantic Modeling Framework for Large-Scale Job Understanding at LinkedIn
arXiv 2607.24783 · 2026-07-29价值对齐中的个性化、角色设定与预测
Personalization, Personas, and Forecasting in Value Alignment
arXiv 2607.24782 · 2026-07-29检索的三个方面：RAG中文档侧、查询侧和答案侧互补性的因子证据
Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAG
arXiv 2607.24781 · 2026-07-29HOBA：用于自适应在线广告的分层策略性投标代理
HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
arXiv 2607.24779 · 2026-07-29用于在线二阶锥规划的热启动内点法
Warm-Start Interior-Point Methods for Online Second-Order Cone Programming
arXiv 2607.24778 · 2026-07-29用于结构化超材料统一生成设计的引导拓扑分布
Steering topology distributions for unified generative design of architected metamaterials
arXiv 2607.24777 · 2026-07-29JKO-RAG：作为瓦瑟斯坦自由能梯度流的分布检索
JKO-RAG: Distributional Retrieval as Wasserstein Free-Energy Gradient Flow
arXiv 2607.24776 · 2026-07-29同理心与人工智能聊天机器人的人际时刻差距：同理心置换理论的见解
Empathy and the Human-Moment Gaps of AI Chatbots: Insights from Empathy Displacement Theory
arXiv 2607.24775 · 2026-07-29用于核辐射预测的大气扩散引导时空变换器
Atmospheric Diffusion-Guided Spatio-Temporal Transformer for Nuclear Radiation Forecasting
arXiv 2607.24774 · 2026-07-29合适规模推荐（RSR）：数据中心运营中虚拟机的云工作负载共形预测
Right-sizing Recommendations (RSR): Cloud Workload Conformal Prediction for Virtual Machines in Data Center Operations
arXiv 2607.24773 · 2026-07-29RoCo-ACE：用于保留感知知识注入的基于展开的在线蒸馏
RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection
arXiv 2607.24771 · 2026-07-29ProcAgent：一种用于边缘端人机协作的过程性任务指导的智能体框架
ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop
arXiv 2607.24770 · 2026-07-29大语言模型的策略规划与预训练语言覆盖范围成反比
LLM Scheming Inversely Scales with Pretraining Language Coverage
arXiv 2607.24769 · 2026-07-29用于定制产前护理的PATHFinder智能体
PATHFinder Agent for Tailored Prenatal Care
arXiv 2607.24768 · 2026-07-29文本块大小对检索增强生成性能的影响
The Effect of Text Chunk Size on Retrieval-Augmented Generation Performance
arXiv 2607.24767 · 2026-07-29Crystalis：用于协同多视图可视化生成的渐进式成核与语义退火
Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation
arXiv 2607.24766 · 2026-07-29通过事实-启发式-情感状态强制来测量和提高大语言模型中的行为一致性
Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement
arXiv 2607.24765 · 2026-07-29GrocLM：使用大语言模型进行电子商务中的杂货类别推荐
GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models
arXiv 2607.24764 · 2026-07-29用于掩码扩散语言模型的计算感知重掩码评估协议
CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models
arXiv 2607.24763 · 2026-07-29Kernel Forge：用于基于大语言模型的CUDA内核生成与优化的代理框架
Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels
arXiv 2607.24762 · 2026-07-29无需信任的验证：将用户端监督重新构建为日常人机对话交互中的常规认知治理
Verification Without Distrust: Reframing User-Side Oversight as Routine Epistemic Governance in Everyday Human-Chatbot Interaction
arXiv 2607.24761 · 2026-07-29CHaystack：中文文档检索与视觉问答基准测试
CHaystack: Benchmarking Chinese Document Retrieval and VQA
arXiv 2607.24760 · 2026-07-29超越记忆：一种用于异构协作知识工作的带大语言模型代理的模板化基础架构
Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM Agents
arXiv 2607.24759 · 2026-07-29数天内从想法到课堂：利用“氛围编码”从IDE活动日志创建编程过程可视化工具
From Idea to Classroom in Days: Using "Vibe Coding" to Create a Programming Process Visualizer from IDE Activity Logs
arXiv 2607.24757 · 2026-07-29当记忆成为媒介时会失去什么？评估人工智能生成的口述历史可视化
What Gets Lost When Memory Becomes Media? Evaluating AI-Generated Oral History Visualization
arXiv 2607.24756 · 2026-07-29面向对象编程课程中学习者与人工智能交互模式及学业表现
Patterns of Learner-AI Interaction and Academic Performance in an Object-Oriented Programming Course
arXiv 2607.24755 · 2026-07-29CARE-MH：迈向心理健康语言模型的统一、可重现和可比评估
CARE-MH: Towards Unified, Reproducible, and Comparable Evaluation of Mental Health LLMs
arXiv 2607.24754 · 2026-07-29语言作为创造性大语言模型交互的物质界面
Language as a Material Interface for Creative LLM Interaction
arXiv 2607.24753 · 2026-07-29生成式人工智能在建筑设计工作室中的发展与应用
Development and applications of Generative AI in architectural design studios
arXiv 2607.24752 · 2026-07-29停止为我写作：思维AI工具中的生成性拒绝
Stop Writing for Me: Generative Refusal in AI Tools for Thought
arXiv 2607.24751 · 2026-07-29
