Publications

A collection of my research work.

Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization

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.

ICML 2026arXiv
Breaking the Continuum: Discrete Distribution Learning for Structural MRI Reconstruction

Breaking the Continuum: Discrete Distribution Learning for Structural MRI Reconstruction

Tianle Lyu†, Mengjingcheng Mo†, Ting Wen, Zhen Song, Zinan Xiong, Yanjie Zhu*

TL;DR: Models MRI reconstruction as discrete distribution learning to improve structural detail recovery.

CVPR 2026PaperPDF
Retrieval-Guided Contextual Inference for Training-Free Video Anomaly Detection in Low-Light Scenarios

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.

ICMR 2026
Linguistic Relative Policy Optimization for Video Anomaly Reasoning

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.

ICML 2026arXiv
A2Seek: Towards Reasoning-Centric Benchmark for Aerial 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.

NeurIPS 2025NeurIPS D&BarXivProjectData
NexusAD: Exploring the Nexus for Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving

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.

ECCVW 2024Code
Recent Advances for Aerial Object Detection: A Survey

Recent Advances for Aerial Object Detection: A Survey

Jiaxu Leng†, Yongming Ye, Mengjingcheng Mo†, Chenqiang Gao, Ji Gan, Bin Xiao, Xinbo Gao*

Survey of imbalance problems in aerial object detection

CSUR 2024Paper
Difficulty-Guided Variant Degradation Learning for Blind Image Super-Resolution

Difficulty-Guided Variant Degradation Learning for Blind Image Super-Resolution

Jiaxu Leng, Jia Wang, Mengjingcheng Mo, Ji Gan, Wen Lu, Xinbo Gao

Difficulty-guided variant degradation for blind super-resolution

TNNLS 2024Paper
Dual Space Embedding Learning for Weakly Supervised Audio-Visual Violence Detection

Dual Space Embedding Learning for Weakly Supervised Audio-Visual Violence Detection

Yiran Liu, Zhanjie Wu, Mengjingcheng Mo, Ji Gan, Jiaxu Leng, Xinbo Gao

Dual Euclidean-hyperbolic learning for audio-visual violence detection

ICME 2024Paper
Pareto Refocusing for Drone-View Object Detection

Pareto Refocusing for Drone-View Object Detection

Jiaxu Leng, Mengjingcheng Mo, Yinghua Zhou, Chenqiang Gao, Weisheng Li, Xinbo Gao*

Pareto refocusing of challenging regions for drone-view detection

TCSVT 2023Paper
Recent Advances in Small Object Detection

Recent Advances in Small Object Detection

Xinbo Gao, Mengjingcheng Mo, Haitao Wang, Jiaxu Leng*

Survey of recent advances in small object detection

JDAP 2021