Mengyang Wu

About

I am a researcher at Huawei Hong Kong Research Center (HKRC) working on computer vision, image processing, and multimodal learning. My research interests include 3D vision, scene understanding, and VLM/LLM-based agent applications.

Feel free to reach out if you'd like to collaborate or discuss research topics.

Publications

ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation

M Wu*, Y Zhao*, J Cao, M Xu, Z Jiang, X Wang, Q Li, G Hu, S Qin, CW Fu

AAAI Conference on Artificial Intelligence, 2025

Llava-spacesgg: Visual instruct tuning for open-vocabulary scene graph generation with enhanced spatial relations

M Xu*, M Wu*, Y Zhao, JCL Li, W Ou

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

FloorLevel-Net: recognizing floor-level lines with height-attention-guided multi-task learning

M Wu, W Zeng, CW Fu

IEEE Transactions on Image Processing, 2021

KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation

Z Guan, JCL Li, Z Hou, P Zhang, D Xu, Y Zhao, M Wu, J Chen, TT Nguyen, et al.

Empirical Methods in Natural Language Processing (EMNLP), 2025

VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models

M Xu, J Chen, Y Zhao, JCL Li, Y Qiu, Z Du, M Wu, P Zhang, K Li, H Yang, et al.

AAAI Conference on Artificial Intelligence, 2026

Geometrically-plausible and Semantically-consistent Generation of Indoor Panoramas

Z Zeng*, M Wu*, X Li, W Gao, S Jiao, CW Fu

IEEE International Conference on Multimedia and Expo (ICME), 2025

Towards real-world adverse weather image restoration: Enhancing clearness and semantics with vision-language models

J Xu, M Wu, X Hu, CW Fu, Q Dou, PA Heng

European Conference on Computer Vision (ECCV), 2024

Deep recognition of vanishing-point-constrained building planes in urban street views

Z Zeng, M Wu, W Zeng, CW Fu

IEEE Transactions on Image Processing, 2020