CV

Education

• Ph.D. in University of Queensland, 2025-Now
• M.Sc. in Nanyang Technological University, 2023-2025
• B.Eng. in Southeast University, 2019-2023

Work experience

• Mar. 2025 - Jun. 2025: Research Intern
  • StepFun
  • Research topics: AIGC.
• Aug. 2023 - Feb. 2025: Research Assistant
  • The Hong Kong University of Science and Technology (Guangzhou)
  • Research topics: LLM/VLM-based agents in video games, 2D/3D generative model and scene reconstruction, multimodal tasks between biological signals and computer vision.
• Oct. 2022 - Jul. 2023: Research Assistant
  • Sun Yat-sen University
  • Research topics: Semantic segmentation of remote sensing images, the application of graph neural networks in computer vision.

Services

Reviewer of ACM-MM, ICASSP, IJCNN, IEEE Transactions on Intelligent Transportation Systems (T-ITS), Journal of Selected Topics in Signal Processing (JSTSP), Pattern Recognition (PR) and Neurocomputing.

Publications

A Hidden Cable Positioning Detection and AR Visualization System

Wu, J., Ye, X., Fu, H., Hu, H., Zhang, S., Yang, P., Wang, R., Zhang, D., Li, B., Gao, Z., & Sun, S. (2022). A Hidden Cable Positioning Detection and AR Visualization System. Chinese Patent, CN114089271A. Link to this patent

High Precision Detection Method of Plastic Gear Black Spots Defect Based on High Frequency Image Enhancement

Fu, H., Zhang, D., Jiang, L., & Chen, H. (2023). High Precision Detection Method of Plastic Gear Black Spots Defect Based on High Frequency Image Enhancement. Tool Engineering(04), 132-136. Link to this paper

SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving

Fu, H., Sun, L., Shen, Y., & Wu, Y.(2023). SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving. arXiv preprint arXiv:2306.03538. Link to this paper

SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network

Fu, H., Shen, Y., Liu, Y., Li, J., & Zhang, X. (2023). SGCN: A multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network. International Journal of Applied Earth Observation and Geoinformation, 122, 103441. Link to this paper

BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction

Fu, H., Shen, Z., Chin, J. J., & Wang, H. (2023). BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction. arXiv preprint arXiv:2312.14871. Link to this paper

DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild

Fu, H.*, Wang, Y.*, Yang, W., & Wen, B. (2024). DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild. arXiv preprint arXiv:2405.19996. Link to this paper

Step1X-Edit: A Practical Framework for General Image Editing

Liu, S., Han, Y., Xing, P., Yin, F., Wang, R., Cheng, W., Liao, J., Wang, Y., Fu, H., Han, C., Li, G., Peng, Y., Sun, Q., Wu, J., Cai, Y., Ge, Z., Ming, R., Xia, L., Zeng, X., Zhu, Y., Jiao, B., Zhang, X., Yu, G. & Jiang, D. (2025). Step1X-Edit: A Practical Framework for General Image Editing. arXiv preprint arXiv:2405.19996. Link to this paper

HDTCNet: A hybrid-dimensional convolutional network for multivariate time series classification

Gu, Y., Yan, X., Qin, H., Akhtar, N., Yuan, S., Fu, H., Yang, S. & Mian, A. (2025). HDTCNet: A hybrid-dimensional convolutional network for multivariate time series classification. Pattern Recognition, 168, 111837. Link to this paper

WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval

Ren, J., Zhang, G., Fu, H., Wu, P. & Wang, H. (2025). WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval. arXiv:2508.03343. Link to this paper

VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft

Fu, H.*, Ren, J.*, Chai, Q., Ye, D. Cai, Y. & Wang, H. (2025). VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft. EMNLP 2025 Main. Link to this paper

ContextNav: Towards Agentic Multimodal In-Context Learning

Fu, H., Ouyang, Y., Chang, K., Wang, Y., Huang, Z. & Cai, Y. (2025). ContextNav: Towards Agentic Multimodal In-Context Learning. arXiv:2510.04560. Link to this paper