2026-07论文中文摘要
深度学习中的利普希茨连续性：理论基础、估计方法、正则化方法及可验证鲁棒性的系统综述
Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness
arXiv 2607.16329 · 2026-07-22基于参数隔离专家的强度-奇偶集成用于多任务情感识别
Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognition
arXiv 2607.16290 · 2026-07-22受监测自由费米子中的数波动与纠缠光谱参与度
Number Fluctuations and Entanglement-Spectrum Participation in Monitored Free Fermions
arXiv 2607.16278 · 2026-07-22QR-SPPS：通过变分量子本征求解器、自适应变分量子本征求解器反事实策略排序和态密度量子相位估计玻尔兹曼尾部风险量化实现量子原生零售供应链风险模拟
QR-SPPS: Quantum-Native Retail Shock Propagation and Policy Stress Simulator
arXiv 2607.16275 · 2026-07-22通过做梦进行发现：人工记忆中的跨域重组
Discovery by Dreaming: Cross-Domain Recombination in Artificial Memory
arXiv 2607.16256 · 2026-07-22张量内核的算子感知混合精度容差校准
Operator-Aware Mixed-Precision Tolerance Calibration for Tensor Kernels
arXiv 2607.16228 · 2026-07-22从新奇到常态化：追踪2024 - 2026年高等教育中对人工智能认知的变化
From Novelty to Normalisation: Tracking Changing Perceptions of AI in Higher Education, 2024-2026
arXiv 2607.16223 · 2026-07-22偏心率作为放大镜：由偏心中子星-黑洞合并实现的精确种群推断
Eccentricity as a Magnifying Glass: Precision Population Inference Enabled by Eccentric Neutron Star-Black Hole Mergers
arXiv 2607.16136 · 2026-07-22平面下次梯度法最后一次迭代的改进分析
Sharp Dimension Dependence for the Last Iterate of the SubGradient Method
arXiv 2607.15980 · 2026-07-22ProtoDUNE双相液态氩时间投影室的运行与性能
Operation and performance of ProtoDUNE Dual Phase liquid argon time projection chamber
arXiv 2607.15927 · 2026-07-22探索BY3（Y = P，As）单层作为钠离子电池高容量和快速扩散阳极的潜力
Two-Dimensional Hexagonal BX3 (X = P, As) Monolayers as High-Capacity, Fast-Charging Anode Platforms for Lithium- and Sodium-Ion Batteries
arXiv 2607.15514 · 2026-07-22MeanFlowNFT：将前向过程强化学习引入平均速度生成器
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
arXiv 2607.15273 · 2026-07-22用于科学可视化素养的多模态大语言模型基准测试
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
arXiv 2607.15176 · 2026-07-22Nosal图中书尺寸和三角形边的两个问题
Two problems on booksize and triangular edges in Nosal graphs
arXiv 2607.15071 · 2026-07-22迈向标记转移系统的现实大型随机模型及其0-1律
Towards realistic large random models of labeled transition systems and their 0-1 laws
arXiv 2607.15029 · 2026-07-22迈向类人物理智能：用于机器人操作的终身视觉-语言-动作学习
Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation
arXiv 2607.14852 · 2026-07-22覆盖序列与覆盖序列码
Covering Sequences and Covering-Sequences Codes
arXiv 2607.14840 · 2026-07-22用于能量、力、应力和玻恩有效电荷多任务预测的SevenNet-Polar：在ZrO$_2$、Li$_3$PO$_4$和钙钛矿中的开发与应用
SevenNet-Polar for MultiTask Prediction of Energy, Forces, Stress, and Born Effective Charges: Development and Application to ZrO$_2$, Li$_3$PO$_4$, and Perovskites
arXiv 2607.14827 · 2026-07-22在千兆秒差距尺度上实现宇宙网分析：一种用于DisPerSE的多块方法
Enabling Cosmic Web Analysis at Gigaparsec Scales: A Multi Block Approach for DisPerSE
arXiv 2607.14785 · 2026-07-22高信噪比下的随机球面码：错误转变、固定错误数据速率和逆界差距
Random Spherical Codes at High SNR: Error Transitions, Fixed-Error Data Rates, and Converse Gaps
arXiv 2607.14768 · 2026-07-22第十一届ABAW竞赛中的团队RAS：多模态矛盾情绪识别方法
Team RAS in 11th ABAW Competition: Multimodal Ambivalence Recognition Approach
arXiv 2607.14702 · 2026-07-22推进原初前沿：强混合下的宇宙学对撞机特征
Pushing the Primordial Frontier: Cosmological Collider Signatures at Strong Mixing
arXiv 2607.14529 · 2026-07-22RetroAgent：利用大语言模型在结构化记忆中进行搜索以实现智能逆合成规划
RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
arXiv 2607.14512 · 2026-07-22量子自旋玻璃的电路复杂度下界
Circuit complexity lower bounds for quantum spin glasses
arXiv 2607.14384 · 2026-07-22用于Pinterest中高效电子商务分发的深度学习因果检索优化
Deep-learning Causal Retrieval Optimization for Efficient e-commerce Distribution in Pinterest
arXiv 2607.14161 · 2026-07-22重新审视伍尔夫生物传热模型：定向血液焓传输、生物佩克莱数及其对激光诱导热疗的影响
The Wulff bio-heat transfer model revisited: directional blood enthalpy transport, the biological Peclet number, and implications for laser-induced thermal therapy
arXiv 2607.14017 · 2026-07-22有限生成自由群的波斯特对应问题是不可判定的
The Post Correspondence Problem for free groups is undecidable
arXiv 2607.13951 · 2026-07-22递归ArUco标记：一种用于无人机着陆垫的可扩展基准标记设计
Recursive ArUco Markers: A Scalable Fiducial Marker Design for Unmanned Aerial Vehicle Landing Pads
arXiv 2607.13830 · 2026-07-22基于肖特基谱的稳健电子感应加速器调谐测量：经典与深度学习互补范式
Robust Betatron-Tune Measurement from Schottky Spectra: Complementary Classical and Deep-Learning Paradigms
arXiv 2607.13791 · 2026-07-22用于支持6G的联网自动驾驶车辆的基于VAE的多任务卫星辅助语义通信框架
A VAE-Driven Multi-Task Satellite-Aided Semantic Communication Framework for 6G-Enabled Connected Autonomous Vehicles
arXiv 2607.13494 · 2026-07-22用于自我改进系统的可证伪发布门限
Falsifiable Release Gates for Self-Improving Systems: Standing Invariants at Scale
arXiv 2607.13070 · 2026-07-22抵抗与更新：用于激励兼容大语言模型的反事实报告坐标
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
arXiv 2607.12985 · 2026-07-22关于映射\(\phi(X,Y)=(Y,X + Y^D + b)\)典范高度的下界
On lower bounds for canonical heights of the map $ϕ(X,Y)=(Y,X+Y^D+b)$
arXiv 2607.12668 · 2026-07-22用于肌肉骨骼护理的基于证据的人工智能
Evidence-Grounded AI for Musculoskeletal Care
arXiv 2607.12527 · 2026-07-22停止在研究中使用媒体偏见/事实核查
Stop using Media Bias/Fact Check in research
arXiv 2607.12108 · 2026-07-22关于贝兹 - 杜阿尔特准则的几点注记
A few remarks on the Baez-Duarte Criterion
arXiv 2607.12084 · 2026-07-22信念与现实的分离存在于语言模型中共享值槽的路由中
Belief-reality separation lives in routing over a shared value slot in language models
arXiv 2607.11945 · 2026-07-22狄利克雷扰动下的塞林问题：几何紧致性与尖锐平面稳定性
Serrin's Problem under Dirichlet Perturbations: Geometric Compactness and Sharp Planar Stability
arXiv 2607.11812 · 2026-07-22屈服应力流体中的通用标度和切换熵
Universal scalings and switching entropy in yield-stress fluids
arXiv 2607.11799 · 2026-07-22CR-Solver：用于腱驱动连续体机器人的GPU加速运动学求解器
CR-Solver: GPU-Accelerated Kinematics Solver for Tendon-driven Continuum Robots
arXiv 2607.11340 · 2026-07-22AdvNav：视觉语言导航中基于行为引导的黑盒对抗攻击
AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation
arXiv 2607.11063 · 2026-07-22某些皮卡秩为一的簇上合冲丛的稳定性
Stable and unstable syzygy bundles on certain Picard rank one varieties
arXiv 2607.10585 · 2026-07-22ARMOR：使用离策略锚样本稳定在线大语言模型强化学习
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
arXiv 2607.10481 · 2026-07-22一种机制用于多种心理空间：语言模型中基于值槽的共享路由器
One mechanism for many mental spaces: a shared router over a value slot in language models
arXiv 2607.10248 · 2026-07-22存在磁场时量子电动力学顶点与反常磁矩
QED vertex and anomalous magnetic moment in the presence of a magnetic field
arXiv 2607.10015 · 2026-07-22LieBN：李群上的批量归一化
LieBN: Batch Normalization over Lie Groups
arXiv 2607.08783 · 2026-07-22有限伯努利卷积中的混沌
Chaos in the Order of Finite Bernoulli Convolutions
arXiv 2607.08676 · 2026-07-22用于在线变点检测的校准持久拉普拉斯累积和
Online Change-Point Detection with Persistent Laplacian Features
arXiv 2607.08635 · 2026-07-22三百项目：通过星系团的模拟X射线和毫米波分析验证$H_0$推断
The Three Hundred Project: Validating $H_0$ inference from mock X-ray and millimetre analyses of galaxy clusters
arXiv 2607.08613 · 2026-07-22将JEPA风格的预测学习应用于JA4衍生的网络指纹
Applying JEPA-Style Predictive Learning to JA4-Derived Network Fingerprints
arXiv 2607.08465 · 2026-07-22
