Mengjingcheng Mo莫梦竟成
Ph.D. Candidate
Chongqing University of Posts and Telecommunications
Research Interests
About
I am a Ph.D. candidate in Computer Science and Technology at Chongqing University of Posts and Telecommunications, advised by Prof. Xinbo Gao (高新波) and Associate Prof. Jiaxu Leng (冷佳旭). My current research focuses on Active Anomaly Understanding, with interests in video anomaly understanding, active visual reasoning, and multimodal large language models.
My recent work studies how vision-language agents can actively acquire evidence, reason over anomalous events, and understand challenging real-world scenarios such as aerial anomalies, low-light surveillance, and autonomous-driving corner cases.
News
Two ICML 2026 papers on active video anomaly understanding and video anomaly reasoning are now available on arXiv.
Updated the research profile around agentic anomaly understanding, active visual reasoning, and multimodal video analysis.
Selected Publications
View All →Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization
Mengjingcheng Mo, Jiaxu Leng, Xinbo Gao*
TL;DR: Learns when and where to watch video evidence for more reliable anomaly reasoning.
Retrieval-Guided Contextual Inference for Training-Free Video Anomaly Detection in Low-Light Scenarios
Mengjingcheng Mo, Jiankang Zheng, Jiaxu Leng, Xinbo Gao*
TL;DR: Uses retrieval-guided context to adapt video anomaly detection under low-light conditions without training.
Linguistic Relative Policy Optimization for Video Anomaly Reasoning
Jiaxu Leng, Jiankang Zheng, Mengjingcheng Mo, Zhanjie Wu, Haosheng Chen, Ji Gan, Xinbo Gao*
TL;DR: Optimizes linguistic reasoning traces for stronger video anomaly understanding.
A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
Mengjingcheng Mo, Xinyang Tong, Mingpi Tan, Jiaxu Leng*, Jiankang Zheng, Yiran Liu, Haosheng Chen, Ji Gan, Weisheng Li, Xinbo Gao*
TL;DR: 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
Mengjingcheng Mo, Jingxin Wang, Like Wang, Haosheng Chen, Changjun Gu, Jiaxu Leng, Xinbo Gao*
TL;DR: Connects multimodal perception and explanation for autonomous-driving corner cases.
Projects
Research projects, curated surveys, and open resources around agentic visual reasoning and anomaly understanding.
Awesome Thinking with VAD
Reasoning-centric video anomaly understanding
A curated collection of papers, datasets, and resources tracking the shift from frame-level video anomaly detection to LLM/VLM-enabled anomaly understanding.
Awesome Thinking with PI
Perception and interaction for visual reasoning
A structured resource map for visual reasoning, perception-driven interaction, tool-augmented multimodal reasoning, and embodied intelligence.
A2Seek
Reasoning-centric benchmark for aerial anomaly understanding
A benchmark and project page for active evidence acquisition and reasoning-centric aerial anomaly understanding.
NexusAD
Corner-case perception and comprehension for autonomous driving
A multimodal autonomous driving corner-case comprehension project built around perception, explanation, and scenario understanding.