{"total":64,"rows":[{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2412.06878","title":"SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations","created":"2024-12-09","cited_by_count":38,"area":"safety"},{"id":"2409.01980","title":"Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey","created":"2024-09-03","cited_by_count":27,"area":null},{"id":"2409.05383","title":"Deep Learning for Video Anomaly Detection: A Review","created":"2024-09-09","cited_by_count":27,"area":null},{"id":"2412.01095","title":"VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models","created":"2024-12-02","cited_by_count":24,"area":"mllm"},{"id":"2505.19877","title":"Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2505.23504","title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","created":"2025-05-29","cited_by_count":24,"area":null},{"id":"2509.26386","title":"PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer","created":"2025-09-30","cited_by_count":19,"area":"agents"},{"id":"2510.22693","title":"VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree","created":"2025-10-26","cited_by_count":18,"area":null},{"id":"2503.13195","title":"Deep Learning Advancements in Anomaly Detection: A Comprehensive Survey","created":"2025-03-17","cited_by_count":17,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2505.15205","title":"Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2511.00962","title":"A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis","created":"2025-11-02","cited_by_count":12,"area":null},{"id":"2502.18863","title":"Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2503.03562","title":"Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection","created":"2025-03-05","cited_by_count":10,"area":null},{"id":"2512.12675","title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","created":"2025-12-14","cited_by_count":10,"area":null},{"id":"2412.07183","title":"Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2507.17394","title":"HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2412.18298","title":"Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight","created":"2024-12-24","cited_by_count":8,"area":"lr"},{"id":"2503.13160","title":"Language-guided Open-world Video Anomaly Detection under Weak Supervision","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2507.21507","title":"VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding","created":"2025-07-29","cited_by_count":8,"area":null},{"id":"2510.02155","title":"Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting","created":"2025-10-02","cited_by_count":8,"area":"mllm"},{"id":"2506.12992","title":"SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models","created":"2025-06-15","cited_by_count":4,"area":null},{"id":"2512.17601","title":"HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2601.08155","title":"Instance-Aligned Captions for Explainable Video Anomaly Detection","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2602.24021","title":"Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection","created":"2026-02-27","cited_by_count":4,"area":"mllm"},{"id":"2501.08470","title":"Detecting Contextual Anomalies by Discovering Consistent Spatial Regions","created":"2025-01-14","cited_by_count":3,"area":null},{"id":"2502.06911","title":"Foundation Models for Anomaly Detection: Vision and Challenges","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2507.02074","title":"Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2510.23190","title":"Evaluation of Vision-LLMs in Surveillance Video","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2603.19098","title":"TAU-R1: Visual Language Model for Traffic Anomaly Understanding","created":"2026-03-19","cited_by_count":3,"area":"mllm"},{"id":"2509.11605","title":"DUAL-VAD: Dual Benchmarks and Anomaly-Focused Sampling for Video Anomaly Detection","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2512.03101","title":"ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification","created":"2025-12-01","cited_by_count":2,"area":"mllm"},{"id":"2602.03328","title":"GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2605.02912","title":"Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models","created":"2026-04-07","cited_by_count":2,"area":"lr"},{"id":"2607.00654","title":"Linguistic Relative Policy Optimization for Video Anomaly Reasoning","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2608.11820","title":"TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2503.00049","title":"Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2503.10508","title":"Hoi2Threat: An Interpretable Threat Detection Method for Human Violence Scenarios Guided by Human-Object Interaction","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2511.00580","title":"TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2512.06840","title":"CADE: Continual Weakly-supervised Video Anomaly Detection with Ensembles","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2601.02927","title":"PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understanding","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2602.08882","title":"Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionals","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2602.18019","title":"DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE","created":"2026-02-20","cited_by_count":1,"area":"moe"},{"id":"2605.15325","title":"COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2608.10317","title":"From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning","created":"2026-08-10","cited_by_count":1,"area":"lr"},{"id":"2504.05254","title":"Explaining Low Perception Model Competency with High-Competency Counterfactuals","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2507.22099","title":"Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2508.06189","title":"MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration","created":"2025-08-08","cited_by_count":0,"area":"agents"},{"id":"2509.18571","title":"Live-E2T: Real-time Threat Monitoring in Video via Deduplicated Event Reasoning and Chain-of-Thought","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2510.20268","title":"GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.10165","title":"Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2602.01004","title":"SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2603.25467","title":"GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Grids","created":"2026-03-26","cited_by_count":0,"area":"lr"},{"id":"2605.15054","title":"LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.31196","title":"Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2608.11260","title":"Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning","created":"2026-08-07","cited_by_count":0,"area":"lr"},{"id":"2608.24937","title":"Multi-Modal Anomaly Detection: A Survey","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25935","title":"TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding","created":"2026-08-26","cited_by_count":0,"area":"rag"},{"id":"2609.06360","title":"NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection","created":"2026-09-06","cited_by_count":0,"area":"mllm"},{"id":"2609.07941","title":"ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.19201","title":"EvoSherlock: Towards Agentic Lifelong Evolution for Unseen Long-Tailed Security-Critical Events in Videos","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2610.01754","title":"Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02019","title":"Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}