SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/Tom-roujiang/MSAD
Terminology
Sources
- Qwen3-VL Technical Report
- QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection
- Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
- Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method
- Xiaomi MiMo-VL-Miloco Technical Report
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
- Ovis2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Kimi-VL Technical Report
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
- AssistPDA: An Online Video Surveillance Assistant for Video Anomaly Prediction, Detection, and Analysis
- SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning
- VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs