相关论文: M3-AD: Reflection-aware Multi-modal, Multi-categor…

Multimodal large language models have recently shown promising progress in visual mathematical reasoning. However, their performance is often limited by a critical yet underexplored bottleneck: inaccurate visual perception. Through…

Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability arises from a fundamental limitation: their reasoning is largely…

Empowering large language models (LLMs) with effective tool utilization capabilities is crucial for enabling AI agents to solve complex problems. However, current models face two major limitations: (1) unreliable tool planning and…

Performing anomaly detection in hybrid systems is a challenging task since it requires analysis of timing behavior and mutual dependencies of both discrete and continuous signals. Typically, it requires modeling system behavior, which is…

Recently, large vision and language models have shown their success when adapting them to many downstream tasks. In this paper, we present a unified framework named CLIP-ADA for Anomaly Detection by Adapting a pre-trained CLIP model. To…

Real-world industrial inspection requires not only localizing defects, but also explaining them in natural language and generating controlled defect edits. However, existing approaches fail to jointly support all three capabilities within a…

Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity, which collectively undermine the robustness of risk…

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to image-level anomaly detection and textual reasoning, while…

In the domain of anomaly detection, methods often excel in either high-level semantic or low-level industrial benchmarks, rarely achieving cross-domain proficiency. Semantic anomalies are novelties that differ in meaning from the training…

Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplishes anomaly detection for multiple classes with a unified…

Video anomaly detection (VAD) is essential for enhancing safety and security by identifying unusual events across different environments. Existing VAD benchmarks, however, are primarily designed for general-purpose scenarios, neglecting the…

Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple…

Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models truly understand the content they process. Crucially, can VLMs detect when a reasoning process…

Industrial 3D anomaly detection performance is fundamentally constrained by the scarcity and long-tailed distribution of abnormal samples. To address this challenge, we propose Synthesis4AD, an end-to-end paradigm that leverages…

Humans detect real-world object anomalies by perceiving, interacting, and reasoning based on object-conditioned physical knowledge. The long-term goal of Industrial Anomaly Detection (IAD) is to enable machines to autonomously replicate…

Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making. To address these limitations, we…

Industrial anomaly detection (IAD) has garnered significant attention and experienced rapid development. However, the recent development of IAD approach has encountered certain difficulties due to dataset limitations. On the one hand, most…

The surface quality inspection of manufacturing parts based on 3D point cloud data has attracted increasing attention in recent years. The reason is that the 3D point cloud can capture the entire surface of manufacturing parts, unlike the…

Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing RL-based approaches…

Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitations. The fundamental…