2026-07论文中文摘要
Chronos漏洞：智能AI中基于时间持久性和内存欺骗的分类法
The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI
arXiv 2607.19433 · 2026-07-23ChainWatch：基于杀伤链的顺序检测框架，用于基于MCP的人工智能代理系统中的多步攻击
ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems
arXiv 2607.19432 · 2026-07-23BRIM：工作负载平衡的双边位串行稀疏推理加速器
BRIM: Workload-Balanced Dual-Sided Bit-Serial Sparse Inference Accelerator
arXiv 2607.19431 · 2026-07-23用于基于脑电图的可解释诊断的自适应多专家图变换器
Adaptive Multi-Expert Graph Transformer for Interpretable EEG-Based Diagnostics
arXiv 2607.19429 · 2026-07-23通过恒星形成星系和活动星系核的演化来阐明死亡类星体和星系规模减小现象
Clarifying Dead Quasars and Downsizing through the Evolution of Star-Forming Galaxies and Active Galactic Nuclei
arXiv 2607.19428 · 2026-07-23二级K3包的积分磁性：CM西塔提升和2-同构迹收缩
Integral magneticity of the level-two K3 packet: CM theta lifts and a 2-isogeny trace contraction
arXiv 2607.19427 · 2026-07-232026年波动问题摘要集
Waves 2026 Book of Abstracts
arXiv 2607.19425 · 2026-07-23JailMeter：一种基于证据的大语言模型越狱攻击评估框架
JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models
arXiv 2607.19424 · 2026-07-23修正：无N偏序集与正交模性
Correction: N-free posets and orthomodularity
arXiv 2607.19423 · 2026-07-23流动性-利润动态的聚合模型
Aggregate models of liquidity-profit dynamics
arXiv 2607.19422 · 2026-07-23Opto-ViT-v2：用于光子近传感器视觉Transformer加速器的抗噪声片上微调
Opto-ViT-v2: Noise-Resilient On-Chip Fine-Tuning for Photonic Near-Sensor Vision Transformer Accelerators
arXiv 2607.19421 · 2026-07-23与费马两平方和相关的定理
Theorems Related to Fermat's Sums of Two Squares
arXiv 2607.19420 · 2026-07-23二维相继式演算中所有*连接词的推理行为语义
Inference-Behaviour Semantics for All$^\ast$ Connectives in Two-Dimensional Sequent Calculi
arXiv 2607.19419 · 2026-07-23e和π的无理性
The Irrationality of $e$ and $π$
arXiv 2607.19418 · 2026-07-23实现对患有脑瘫的儿童检测与运动相关的皮层电位的脑机接口系统的快速校准
Enabling Rapid Calibration of BCI Systems that Detect Movement-Related Cortical Potentials in Children with Cerebral Palsy
arXiv 2607.19417 · 2026-07-23一个5阶的恰当欧拉幻方矩阵
A proper Euler magic matrix of order $5$
arXiv 2607.19416 · 2026-07-23纵向细胞绘画形态学的检索增强大语言模型假设审计
Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology
arXiv 2607.19415 · 2026-07-23科瓦尔斯基 - 斯洛姆钦斯卡的两个问题
Two questions of Kowalski-Słomczyńska
arXiv 2607.19414 · 2026-07-23论非常规离散化
On unconventional discretisations
arXiv 2607.19413 · 2026-07-23关于广义彼得森图P(n,3)零强迫数的修正
A correction to the Zero Forcing Number of the Generalized Petersen Graphs $P(n,3)$
arXiv 2607.19412 · 2026-07-23由拉普拉斯钩子不变多项式确定的几乎完全图
Almost complete graphs determined by Laplacian hook immanantal polynomials
arXiv 2607.19411 · 2026-07-23计算不含固定长度非递减子词的单词数量
Counting words without non-decreasing subwords of fixed length
arXiv 2607.19410 · 2026-07-23FORCE-Bench：企业金融中智能代理人工智能的基准测试、数据集和评估工具
FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance
arXiv 2607.19409 · 2026-07-23语言模型微调中基于奖励感知的进化策略种群规模缩放
Reward-Aware Population Scaling of Evolutionary Strategies in LLM Fine-Tuning
arXiv 2607.19408 · 2026-07-23ITPEval：跨交互式定理证明器的形式化翻译基准测试
ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers
arXiv 2607.19407 · 2026-07-23核磁共振解析作为一个智能体搜索问题，而非建模问题
NMR Elucidation as an Agentic Search Problem, Not a Modeling Problem
arXiv 2607.19406 · 2026-07-23再现循环变换器：思维链变换器
Reproducing Recurrent Transformers: The CoTFormer
arXiv 2607.19405 · 2026-07-23在差分隐私下恢复临床效用：异构心血管数据集上自适应联邦聚合的实证验证
Recovering Clinical Utility Under Differential Privacy: Empirical Validation of Adaptive Federated Aggregation on Heterogeneous Cardiovascular Datasets
arXiv 2607.19403 · 2026-07-23在医学图像分割中，何时一致性优于投票？统计标签融合的批判性分析
When Does Consensus Beat Voting? A Critical Analysis of Statistical Label Fusion in Medical Image Segmentation
arXiv 2607.19402 · 2026-07-23用于头颈部动态对比增强磁共振成像中非线性运动抑制的柯普曼算子谱分解
Koopman-Operator Spectral Decomposition for Nonlinear Motion Suppression in Dynamic Contrast-Enhanced MRI of the Head and Neck
arXiv 2607.19401 · 2026-07-23用于基因调控和衰老的具有隐私保护表格学习的预测性单细胞基础模型
Predictive single cell foundation model for gene regulation and aging with privacy-preserving tabular learning
arXiv 2607.19400 · 2026-07-23在大规模视觉-语言-动作模型中利用离线监督实现高效且通用的强化学习
Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models
arXiv 2607.19399 · 2026-07-23HyGRL：用于多实体问题的自适应混合图推理
HyGRL: Adaptive Hybrid Graph Reasoning for Multi-Entity Questions
arXiv 2607.19398 · 2026-07-23内存合并深度Q网络：用于稳定值学习的灵敏度加权目标更新
Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning
arXiv 2607.19397 · 2026-07-23从轨迹到前缀：通过重放前缀和在线延续复用教师轨迹
From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation
arXiv 2607.19395 · 2026-07-23基于共享空间对齐的跨主体语义解码用于广义神经表征学习
Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning
arXiv 2607.19394 · 2026-07-23可解码但不可检测：用于近离群点基准测试的泄漏指纹
Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks
arXiv 2607.19393 · 2026-07-23使用图神经网络预测地下水中的砷浓度
Predicting Groundwater Arsenic Concentrations Using Graph Neural Networks
arXiv 2607.19392 · 2026-07-23LAARA：用于参数高效微调的层感知自适应秩分配
LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning
arXiv 2607.19391 · 2026-07-23通过分箱谱损失在非结构化网格上进行混沌动力学的尺度感知学习
Scale-Aware Learning of Chaotic Dynamics on Unstructured Meshes via Binned Spectral Losses
arXiv 2607.19387 · 2026-07-23构建快速，评估缓慢：管道选择主导自动可解释性得分方差
Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance
arXiv 2607.19386 · 2026-07-23STN-TGAT：通过具有可学习软阈值稀疏化的先验引导图注意力进行前K投资组合构建
STN-TGAT: Top-K Portfolio Construction via Prior-Guided Graph Attention with Learnable Soft-Threshold Sparsification
arXiv 2607.19385 · 2026-07-23SUM：用于联邦类增量学习的时空适应向量统一几何手术
SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning
arXiv 2607.19384 · 2026-07-23趋势强度预测生成式基础模型何时获胜：功率控制基准、机制及可操作的选择规则
Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule
arXiv 2607.19383 · 2026-07-23时间序列预测持续学习中的可解释性挑战
Challenges of Explainability in Continual Learning for Time Series Forecasting
arXiv 2607.19382 · 2026-07-23空气质量竞技场：一个大规模多区域地面监测数据集以及基于时间序列基础模型的空气质量预测基准
Air Quality Arena: A Large-Scale Multi-Region Ground Monitoring Dataset and Benchmark for Air Quality Forecasting with Time-Series Foundation Models
arXiv 2607.19381 · 2026-07-23CruiseBench：用于发动机剩余使用寿命预测的真实飞行对齐N-CMAPSS基准测试
CruiseBench: A Real-Flight-Aligned N-CMAPSS Benchmark for Engine RUL Prediction
arXiv 2607.19380 · 2026-07-23用于模型选择的贝叶斯风洞
Bayesian Wind Tunnels for Model Selection
arXiv 2607.19379 · 2026-07-23用于稳健学习具有挑战性的偏微分方程的可靠性感知硬软物理信息神经网络
Reliability-Aware Hard--Soft Physics-Informed Neural Networks for Robust Learning of Challenging Partial Differential Equations
arXiv 2607.19377 · 2026-07-23Refnd：防止关系型数据集中的数据泄露
Refnd: Preventing Data Leakage in Relational Datasets
arXiv 2607.19376 · 2026-07-23
