2026-08论文中文摘要
鲁棒双模型协作随机向量函数链接网络
Robust Dual-Model Collaborative Random Vector Functional Link Network
arXiv 2608.13628 · 2026-08-17用于超导量子比特高保真度读出的可扩展边沿通Purcell滤波器
A scalable edge-pass Purcell filter for high-fidelity readout of superconducting qubits
arXiv 2608.13627 · 2026-08-17内部动作图的校准测试：无全局仿射闭包的状态信号
A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
arXiv 2608.13626 · 2026-08-17用于信号时序逻辑的奖励机
Reward Machines for Signal Temporal Logic
arXiv 2608.13625 · 2026-08-17基于语义感知偏差估计的大音频语言模型公平性测量
Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation
arXiv 2608.13624 · 2026-08-17ARC：开放式真实世界交互中的公平相对优势比较
ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction
arXiv 2608.13622 · 2026-08-17你的概率联合嵌入预测架构（JEPA）本质上是隐马尔可夫模型：联合嵌入预测学习的状态空间解释
Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning
arXiv 2608.13621 · 2026-08-17暗能量背景下坍缩尘埃形成的正则黑洞
Regular Black Holes from Collapsing Dust in a Dark Energy Background
arXiv 2608.13619 · 2026-08-17算法设计与医师责任
Algorithm Design and Physician Liability
arXiv 2608.13618 · 2026-08-17脓毒症治疗的依从性如何？一种专家指导的神经符号管道用于生成临床依从性见解
How Compliant is Sepsis Treatment? An Expert-Guided Neuro-symbolic Pipeline for Generating Clinical Compliance Insights
arXiv 2608.13617 · 2026-08-17基于邻接矩阵的移动通信智能体的谱代理控制
Adjacency-Based Spectral Proxy Control of Mobile Communication Agents
arXiv 2608.13616 · 2026-08-17泊松-沃罗诺伊与泊松-德劳内镶嵌中的典型单元体积分布综述：分析理论、高维极限及无线应用
A Survey of Typical-Cell Volume Distributions in Poisson--Voronoi and Poisson--Delaunay Tessellations: Analytical Theory, High-Dimensional Limits, and Wireless Applications
arXiv 2608.13615 · 2026-08-17VoiceDesigner：基于统一扩散建模与数据增强的文本到语音生成与编辑
VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentation
arXiv 2608.13613 · 2026-08-17SemPlan：面向企业数据的基于大语言模型（LLM）查询的结构化语义规划基准测试
SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data
arXiv 2608.13612 · 2026-08-17LoopVSR：用于自动修复视觉语音识别推理流水线的循环工程框架
LoopVSR: A Loop Engineering Framework for Automated Repair of Visual Speech Recognition Inference Pipelines
arXiv 2608.13610 · 2026-08-17基于缩放假设的无标签智能体学习控制器能力评估
Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis
arXiv 2608.13608 · 2026-08-17没有通用信号可预测版本更新下的样本级大语言模型退化
No Universal Signal Predicts Sample-Level LLM Regression under Version Updates
arXiv 2608.13607 · 2026-08-17用于具身消歧的主动感知
Active Perception for Embodied Disambiguation
arXiv 2608.13605 · 2026-08-17误解产生、放大与检测的跨学科分类与建模：从语用学到智能体
Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents
arXiv 2608.13604 · 2026-08-17流体-流体及固相界面的一阶热力学平衡条件
On first-order thermodynamic equilibrium conditions for fluid-fluid and solid-phase interfaces
arXiv 2608.13603 · 2026-08-17困难样本与错误标签：在有界标签噪声下测试不确定性采样中的错误暴露与错误定位
Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
arXiv 2608.13601 · 2026-08-17控制任务中的持续进化策略
Continual Evolution Strategies in Control Tasks
arXiv 2608.13600 · 2026-08-17以秘密-隐写图像的差异性为设计轴：基于扩散模型的可逆无载体图像隐写术
Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models
arXiv 2608.13597 · 2026-08-17通过激活引导剪枝实现跨模型规模的无训练知识迁移
Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
arXiv 2608.13596 · 2026-08-17迈向视频数据定性分析的规模化
Towards Scaling Qualitative Analysis of Video Data
arXiv 2608.13594 · 2026-08-17施泰纳4链半径的可行性问题
Feasibility problem for the radii of Steiner 4-chains
arXiv 2608.13593 · 2026-08-17大语言模型中的稳定校准误差：高置信度错误的实用视角
Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors
arXiv 2608.13591 · 2026-08-17用于回归的鲁棒XGBoosting
Robust XGBoosting for Regression
arXiv 2608.13590 · 2026-08-17面向月球舱外活动（EVA）程序指导的上下文感知AI助手与AR界面
Context Aware AI Assistant and AR Interface for Lunar Extravehicular Activity (EVA) Procedural Guidance
arXiv 2608.13589 · 2026-08-17IterCOMP：面向多跳问答的感知推理自适应提示压缩
IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering
arXiv 2608.13588 · 2026-08-17学生与ChatGPT交互可视化：为英语作为外语写作教育设计教师仪表盘
Student-ChatGPT Interaction Visible: Designing a Teacher Dashboard for EFL Writing Education
arXiv 2608.13587 · 2026-08-17超越简化：用于阅读障碍友好型教育文本中保真视觉可访问性的DFT-GEN
Beyond Simplification: DFT-GEN for Fidelity-Preserving Visual Accessibility in Dyslexia-Friendly Educational Texts
arXiv 2608.13583 · 2026-08-17规制、权力与合规悖论：智能家居的纵向研究
Regulation, Power, and the Compliance 1 Paradox: A Longitudinal Study of Smart Homes
arXiv 2608.13582 · 2026-08-17从预测到干预：基于大语言模型智能体的个性化餐级血糖调节
From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent
arXiv 2608.13581 · 2026-08-17Jais 2：以阿拉伯语为核心的开源大语言模型家族
Jais 2: A Family of Arabic-Centric Open Large Language Models
arXiv 2608.13580 · 2026-08-17BCMT：分块因果记忆Transformer
BCMT: Blockwise Causal Memory Transformer
arXiv 2608.13578 · 2026-08-17AI评估应与人类协同开展
AI Evaluation Should Work With Humans
arXiv 2608.13577 · 2026-08-17BCIJelly：用于脑机接口研究的集成生态系统
BCIJelly: An integrated ecosystem for brain-computer interface research
arXiv 2608.13576 · 2026-08-17基于聚合类激活图的网络数据全局解释交互式分析
Interactive Analysis of Global Explanations using Aggregated Class Activation Maps for Network Data
arXiv 2608.13575 · 2026-08-17架构师（The Architect）：直接在微软 Excel 中实现深度学习数学的交互式可视化工具
The Architect: Interactive Visualization of Deep Learning Mathematics Directly in Microsoft Excel
arXiv 2608.13572 · 2026-08-17并非所有token都平等：面向智能体大语言模型系统的感知通胀路由
Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
arXiv 2608.13571 · 2026-08-17在潜空间思考，以语言解释：自解释潜推理
Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
arXiv 2608.13570 · 2026-08-17用于结构化几何图形标注的双验证器网页界面
A Two-Validator Web Interface for Structured Geometry Figure Annotation
arXiv 2608.13569 · 2026-08-17语言服务器能为编码智能体节省 token 吗？一种测量方法与初步研究
Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study
arXiv 2608.13568 · 2026-08-17大型语言模型中出现的模块化认知架构
Modular Cognitive Architecture Emerges in Large Language Models
arXiv 2608.13567 · 2026-08-17勿宣称面向基准的优化可提升通用编码能力——需要多样化评估
Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required
arXiv 2608.13566 · 2026-08-17基于幅值型专家掩码的混合专家模型的深度感知敏感性分析
Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking
arXiv 2608.13565 · 2026-08-17生成无奖励的评判标准以减少智能体评估中的过度打分
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
arXiv 2608.13564 · 2026-08-17代理验证的大语言用户体验微模拟：一种用于早期决策支持的工件优先协议
Proxy-Validated LLM UX Micro-Simulations: An Artifact-First Protocol for Early-Stage Decision Support
arXiv 2608.13563 · 2026-08-17L-FNO：用于随机事件动力学的洛伦兹傅里叶神经算子
L-FNO: Lorentzian Fourier Neural Operator for Stochastic Event Dynamics
arXiv 2608.13562 · 2026-08-17
