惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

C
Comments on: Blog
S
Schneier on Security
Microsoft Azure Blog
Microsoft Azure Blog
T
Tor Project blog
V
Visual Studio Blog
C
CXSECURITY Database RSS Feed - CXSecurity.com
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Spread Privacy
Spread Privacy
月光博客
月光博客
罗磊的独立博客
Cisco Talos Blog
Cisco Talos Blog
P
Privacy International News Feed
T
Tenable Blog
阮一峰的网络日志
阮一峰的网络日志
AWS News Blog
AWS News Blog
T
ThreatConnect
博客园 - 三生石上(FineUI控件)
Recorded Future
Recorded Future
Hugging Face - Blog
Hugging Face - Blog
T
Tailwind CSS Blog
博客园 - 叶小钗
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
A
Arctic Wolf
L
LINUX DO - 最新话题
美团技术团队
大猫的无限游戏
大猫的无限游戏
I
Intezer
博客园 - 司徒正美
酷 壳 – CoolShell
酷 壳 – CoolShell
量子位
小众软件
小众软件
T
Threatpost
V
V2EX
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
宝玉的分享
宝玉的分享
The Register - Security
The Register - Security
Project Zero
Project Zero
J
Java Code Geeks
Cyberwarzone
Cyberwarzone
IT之家
IT之家
MyScale Blog
MyScale Blog
T
Threat Research - Cisco Blogs
T
The Blog of Author Tim Ferriss
腾讯CDC
S
SegmentFault 最新的问题
F
Fox-IT International blog
S
Security Archives - TechRepublic
Last Week in AI
Last Week in AI
G
GRAHAM CLULEY
M
MIT News - Artificial intelligence

cs.AI updates on arXiv.org

Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation On the Impact of Class Imbalance on the Learning Dynamics of Deep Neural Networks:An Intuitive Insight Mixture of Complementary Agents for Robust LLM Ensemble READER: Reasoning-Enhanced AI-Generated Text Detection Assessing the Operational Viability of Foundation Models for Time Series Forecasting LLM Agent Based Renewable Energy Forecasting Using Edge and IoT Data A Review of Solar Wind Weather and Grid Aware Decision Support Who judges the judges? Governance from metrics: a runtime framework for continuous LLM compliance monitoring Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood? PILOT: Policy-Informed Learned Optimization for Adaptive Deep Network Training Evidence-Linked Radiology Reporting: A Human-Supervised Reference Architecture for Structured Imaging Intelligence Knowledge Graph Modulated Deep Learning for Limited-Sample Clinical Data Analysis Overcoming "Physics Shock" in Earth Observation A Heteroscedastic Uncertainty Framework for PINN-based Flood Inference Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation Feature Lottery? A Bifurcation Theory of Concept Emergence Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges Knowledge Graph-Driven Expert-Level Reasoning for Neuroscience JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack Grammatically-Guided Sparse Attention for Efficient and Interpretable Transformers PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation Raon-Speech Technical Report The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express Simulating Human Memory with Language Models Explainable Retinal Imaging for Prediction of Multi-Organ Dysfunction in Type 2 Diabetes Towards a Universal Causal Reasoner Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing QUIET: A Multi-Blank Cascaded Story Cloze Benchmark for LLM Creative Generation Capability Federated Learning over Human-Body Communication for On-Body Edge Intelligence: A Survey, Taxonomy, and BODYFED-HBC Scheduling Vignette Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs TGFormer: Towards Temporal Graph Transformer with Auto-Correlation Mechanism Eureka: Intelligent Feature Engineering for Enterprise AI Cloud Resource Demand Prediction Extracting Training Data from Diffusion Language Models via Infilling Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation An Interactive Paradigm for Deep Research A general tensor-structured compression scheme for efficient large language models Rethinking Federated Unlearning via the Lens of Memorization Improving Labeling Consistency with Detailed Constitutional Definitions and AI-Driven Evaluation Side-by-side Comparison Amplifies Dialect Bias in Language Models Mimir: Large-scale Multilingual Concept Modeling Measuring the Depth of LLM Unlearning via Activation Patching STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media Batch Normalization Amplifies Memorization and Privacy Risks Treatment Effect Estimation with Differentiated Networked Effect on Graph Data TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering Generative OOD-regularized Model-based Policy Optimization Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis Complement Submodular Information Measures for Balanced and Robust Data Selection A Multi-Agent LLM Framework for Rating the Quality of Surgical Feedback CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling Disentangled Double Machine Learning for Accurate Causal Effect Estimation Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognition World-State Transformations for Neuro-symbolic Interactive Storytelling Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers Not All Transitions Matter: Evidence from PPO Quaternion Self-Attention with Shared Scores Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning Filtered Posterior Mean Collections: A Unified Framework for Analytical Models of Diffusion Generalization Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions By Their Fruits You Will Know Them: Comparing Formalizations of Law by the Decisions They Encode Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning Hidden-State Privacy Has an Empty Middle Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors Document Classification Pattern Recognition via Information Fusion: A Systematic Review of Multimodal and Multiview Representation Approaches Momentum Streams for Optimizer-Inspired Transformers Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints LAPLEX: The FFT of Learnable Laplace Kernels
Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection
Heqiang Wang · 2026-05-26 · via cs.AI updates on arXiv.org

View PDF HTML (experimental)

Abstract:Industrial anomaly detection has attracted significant attention as a fundamental challenge in industrial systems. The rapid advancement of heterogeneous industrial sensors has driven industrial anomaly detection from unimodal to multimodal paradigms. However, existing methods are primarily designed for centralized and offline settings, overlooking the distributed and continuously generated data characteristic of real-world industrial environments. With the advancement of edge intelligence, modern edge devices are increasingly capable of not only data acquisition but also distributed model training, enabling collaborative intelligence across the system. Industrial anomaly detection represents a critical application in this context. Motivated by these challenges, we propose a novel framework termed Multimodal Online Distributed Industrial Anomaly Detection (MODIAD). We first present a comprehensive workflow for MODIAD and then formulate a Multi-class Intelligent Scheduling (MIS) problem to coordinate cross class model updates by balancing data sufficiency and class update frequency. To efficiently solve this problem, we design a Sequential Marginal Gain Greedy (SMG) algorithm that enables effective multi-class training under resource constraints. Furthermore, to improve the computational and communication efficiency during training, we propose an Resource Efficient Class-Wise Low Rank Adaptation (REC-LoRA) strategy, which significantly reduces system overhead while preserving detection performance. Extensive experiments on two representative multimodal industrial anomaly detection datasets, MVTec 3D-AD and Eyecandies demonstrate that the proposed approach achieves superior performance and efficiency under the MODIAD scenario.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2605.23984 [cs.LG]
  (or arXiv:2605.23984v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2605.23984

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Heqiang Wang [view email]
[v1] Fri, 15 May 2026 08:25:40 UTC (318 KB)