Mengjingcheng Mo https://2-mo.github.io/ PhD candidate at Chongqing University of Posts and Telecommunications focusing on agentic anomaly understanding. en Wed, 01 Jul 2026 11:25:31 GMT Released A2Seek, an active anomaly-seeking benchmark and project page for aerial anomaly understanding. https://2-mo.github.io/ news-2026-05-Released A2Seek, an active anomaly-seeking benchmark and project page for aerial anomaly understanding. Fri, 01 May 2026 00:00:00 GMT Released A2Seek, an active anomaly-seeking benchmark and project page for aerial anomaly understanding. Updated the research profile around agentic anomaly understanding, active visual reasoning, and multimodal video analysis. https://2-mo.github.io/ news-2026-02-Updated the research profile around agentic anomaly understanding, active visual reasoning, and multimodal video analysis. Sun, 01 Feb 2026 00:00:00 GMT Updated the research profile around agentic anomaly understanding, active visual reasoning, and multimodal video analysis. Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization https://2-mo.github.io/publications/ publication-mo2026learning Thu, 01 Jan 2026 00:00:00 GMT Learns when and where to watch video evidence for more reliable anomaly reasoning. Breaking the Continuum: Discrete Distribution Learning for Structural MRI Reconstruction https://2-mo.github.io/publications/ publication-lyu2026breaking Thu, 01 Jan 2026 00:00:00 GMT Models MRI reconstruction as discrete distribution learning to improve structural detail recovery. Retrieval-Guided Contextual Inference for Training-Free Video Anomaly Detection in Low-Light Scenarios https://2-mo.github.io/publications/ publication-mo2026retrieval Thu, 01 Jan 2026 00:00:00 GMT Uses retrieval-guided context to adapt video anomaly detection under low-light conditions without training. Linguistic Relative Policy Optimization for Video Anomaly Reasoning https://2-mo.github.io/publications/ publication-leng2026linguistic Thu, 01 Jan 2026 00:00:00 GMT Optimizes linguistic reasoning traces for stronger video anomaly understanding. A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding https://hayneyday.github.io/A2Seek/ publication-mo2025a2seek Wed, 01 Jan 2025 00:00:00 GMT Introduces a benchmark for evaluating reasoning over aerial anomaly evidence. NexusAD: Exploring the Nexus for Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving https://2-mo.github.io/publications/ publication-mo2024nexusad Mon, 01 Jan 2024 00:00:00 GMT Connects multimodal perception and explanation for autonomous-driving corner cases. Recent Advances for Aerial Object Detection: A Survey https://doi.org/10.1145/3664598 publication-leng2024recent Mon, 01 Jan 2024 00:00:00 GMT Survey of imbalance problems in aerial object detection Pareto Refocusing for Drone-View Object Detection https://doi.org/10.1109/TCSVT.2022.3210207 publication-leng2022pareto Sun, 01 Jan 2023 00:00:00 GMT Pareto refocusing of challenging regions for drone-view detection Recent Advances in Small Object Detection https://2-mo.github.io/publications/ publication-gao2021recent Fri, 01 Jan 2021 00:00:00 GMT Survey of recent advances in small object detection