2026-07论文中文摘要
ExaGEMM：通过用于低位GEMM的关联寄存器内计算实现CPU驱动的ML推理的探索框架
ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM
arXiv 2607.14622 · 2026-07-17关于具有伯格曼 - 爱因斯坦度量的斯坦因空间的分类
On the Classification of Stein spaces with Bergman-Einstein metrics
arXiv 2607.14621 · 2026-07-17高斯-博内特扩展斯塔罗宾斯基-麦克斯韦引力中带电黑洞的标量化
Scalarization of Charged Black Hole in Gauss-Bonnet Extended Starobinsky-Maxwell Gravity
arXiv 2607.14620 · 2026-07-17用于复杂仪器设计与优化的机器学习
Machine Learning for Complex Instrument Design and Optimization
arXiv 2607.14619 · 2026-07-17PolyQ：用于可扩展边缘CPU大语言模型推理的端到端量化框架协同设计
PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference
arXiv 2607.14618 · 2026-07-17广义高度约束绑定下无序项树模式的高效模式匹配
Efficient Pattern Matching for Unordered Term Tree Patterns under Generalized Height-Constrained Bindings
arXiv 2607.14617 · 2026-07-17用于有限训练样本不确定性量化的梯度增强样条维分解
Gradient-enhanced spline dimensional decomposition for uncertainty quantification with limited training samples
arXiv 2607.14615 · 2026-07-17超越熵：通过对比策略优化实现正确性感知优势塑造
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
arXiv 2607.14614 · 2026-07-17用于长尾心电图心律失常诊断的角高斯监督对比学习
Angular Gaussian Supervised Contrastive Learning for Long-Tailed Electrocardiogram Arrhythmia Diagnosis
arXiv 2607.14613 · 2026-07-17狄利克雷特征群生成元上狄利克雷L函数的一阶矩
The First Moment of Dirichlet L-functions over Generators of the Character Group
arXiv 2607.14612 · 2026-07-17糟糕的记忆：评估智能体系统中内存引发的提示注入风险
Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems
arXiv 2607.14611 · 2026-07-17通过控制理论引导动态网络中心性
Steering dynamic network centrality via control theory
arXiv 2607.14610 · 2026-07-17用于接触丰富的机器人操作的表示对齐触觉基础
Representation-Aligned Tactile Grounding for Contact-Rich Robotic Manipulation
arXiv 2607.14609 · 2026-07-17映射类群的鲍姆施拉格 - 索利塔子群
Baumslag-Solitar subgroups of the mapping class group
arXiv 2607.14608 · 2026-07-17审计公平性与隐私性的权衡：公平性增强算法的亚群体层面影响
Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms
arXiv 2607.14607 · 2026-07-17一种用于空中目标分类和意图预测的证据推理方法
An Evidential Reasoning Approach for Aerial Target Classification and Intent Prediction
arXiv 2607.14606 · 2026-07-17研究基于大语言模型的自动作文评分中的母语偏见：对托福作文的开放权重人工智能模型进行跨提示评估
Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays
arXiv 2607.14605 · 2026-07-17通过反事实估计加速A/B测试：通过策略重叠降低方差
Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap
arXiv 2607.14604 · 2026-07-17重言式系统与局部上同调
Tautological systems and local cohomology
arXiv 2607.14602 · 2026-07-17SYNAPSE：一个多语言大模型编排的人工智能导师，用于具有神经差异优先设计的安全软件开发教育
SYNAPSE: A Multi-LLM Orchestrated AI Tutor for Secure Software Development Education with Neurodivergent-First Design
arXiv 2607.14601 · 2026-07-17基于梯度优化的非线性模型预测控制视角：一种新型高效、无参数且可证明稳定的算法
A Nonlinear Model Predictive Control Perspective on Gradient-Based Optimization: A New Efficient, Parameter-Free and Provably Stable Algorithm
arXiv 2607.14600 · 2026-07-17分圆多项式与映射类类型的同调准则
Cyclotomic polynomials and homological criteria for mapping class types
arXiv 2607.14599 · 2026-07-17一种用于稀疏计数矩阵的具有零训练特征提取的确定性二进制指纹框架
A Deterministic Binary Fingerprinting Framework with Zero-Trained Feature Extraction for Sparse Count Matrices
arXiv 2607.14596 · 2026-07-17高度柔性细长结构弯曲弹性的数值与实验框架
Numerical and experimental framework for bending elasticity of highly flexible slender structures
arXiv 2607.14594 · 2026-07-17量子多核架构中的自适应纠缠管理
Adaptive Entanglement Management in Quantum Multi-Core Architectures
arXiv 2607.14592 · 2026-07-17人工智能生成的反馈效果如何？对20000多篇外语作文草稿的内在和外在评估
How Well Does AI-Generated Feedback Work? Intrinsic and Extrinsic Evaluation across more than 20,000 EFL Essay Drafts
arXiv 2607.14591 · 2026-07-17分子束外延生长的AlScN薄膜的二阶光学非线性
Second-Order Optical Nonlinearity of AlScN Films Grown By Molecular Beam Epitaxy
arXiv 2607.14590 · 2026-07-17用于BCH码的准信念传播和神经网络校验节点处理
Quasi-Belief Propagation and Neural-Network Check Node Processing for BCH Codes
arXiv 2607.14589 · 2026-07-17对话式触觉数据接口：使用可刷新触觉显示器和对话式人工智能与盲人用户共同设计无障碍数据体验
Conversational Tactile Data Interfaces: Co-Designing Accessible Data Experiences with Blind Users Using Refreshable Tactile Displays and Conversational AI
arXiv 2607.14588 · 2026-07-17公共记录中的Qubes操作系统安全性
Qubes OS Security in the Public Record
arXiv 2607.14587 · 2026-07-17SoftNav：将3D场景令牌注入视觉语言模型以进行具身导航
SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation
arXiv 2607.14586 · 2026-07-17治理人工智能：公众偏好与监管选择
Governing Artificial Intelligence: Public Preferences and Regulatory Options
arXiv 2607.14585 · 2026-07-17来自快速全天空氢原子巡天（FASHI）第二数据释放（DR2）的致密高速云团目录
A Catalog of Compact High-Velocity Clouds from the FAST All-Sky HI Survey (FASHI) DR2
arXiv 2607.14584 · 2026-07-17无时间信号且无时间经典性
Exact No Signaling in Time without Temporal Classicality
arXiv 2607.14583 · 2026-07-17MathCoPilot：一种用于数学研究的人机共生范式的交互式系统
MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research
arXiv 2607.14582 · 2026-07-17用于脑肿瘤视觉指令微调的多语言模型协作式MRI报告生成
Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncology
arXiv 2607.14581 · 2026-07-17先进图像生成：负提示优化与潜在分类器引导
Advanced Image Generation: Negative Prompt Optimization and Latent Classifier Guidance
arXiv 2607.14580 · 2026-07-17Skeleton：非视觉数据体验的可视化创作
Skeleton: Visual Authoring of Non-visual Data Experiences
arXiv 2607.14579 · 2026-07-17超越隐式力：在使用Transformer的动作分块中评估显式力-扭矩代理
Beyond Implicit Force: Evaluating Explicit Force-Torque Proxies in Action Chunking with Transformers
arXiv 2607.14578 · 2026-07-17结合簇上的联络
Connections on Associative Varieties
arXiv 2607.14577 · 2026-07-17佩妮：支架式外语写作中学习者与聊天机器人交互的转换网络分析
Penny: Transition Network Analysis of Learner-Chatbot Interactions in Scaffolded EFL Writing
arXiv 2607.14575 · 2026-07-17网络社会实验中多语言模型智能体的协作空间学习
Collaborative Spatial Learning with Multi-LLM Agents in Networked Social Experiments
arXiv 2607.14574 · 2026-07-17脊柱：一条超奇异高速公路
The Spine: A Supersingular Highway
arXiv 2607.14572 · 2026-07-17使智能体部署安全民主化：一种结构监测方法
Democratizing Agent Deployment Safety: A Structural Monitoring Approach
arXiv 2607.14570 · 2026-07-17在最简单的贝尔场景中，没有有限的 NPA 层级能刻画完整的量子集
No Finite NPA Level Characterizes the Complete Quantum Set in the Simplest Bell Scenario
arXiv 2607.14569 · 2026-07-17在6GB 2011 GPU上的现代多模态助手：针对费米架构的阶段验证、全GPU CUDA推理
A Modern Multimodal Assistant on a 6 GB 2011 GPU: Stage-Validated, All-GPU CUDA Inference for Fermi
arXiv 2607.14568 · 2026-07-17基于MITRE ATT&CK的网络威胁情报，使用大语言模型实现全自动端到端对手模拟
Fully Automated End-to-End Adversary Emulation from MITRE ATT\&CK Based Cyber Threat Intelligence Using LLMs
arXiv 2607.14566 · 2026-07-17光子集成电路中的超快可编程布拉格反射
Ultrafast programmable Bragg reflection in photonic integrated circuits
arXiv 2607.14565 · 2026-07-17近似可导航图
Almost Navigable Graphs
arXiv 2607.14564 · 2026-07-17用于从低分辨率和噪声位移数据估计非均匀弹性特性的概率物理信息神经网络
Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data
arXiv 2607.14563 · 2026-07-17
