Portrait
Yuqi Xiong
About Me
I am Yuqi Xiong, a graduate student in Electrical and Computer Engineering at the National University of Singapore. My research interests focus on machine learning, deep learning, big data mining, computer vision, and intelligent autonomous systems. My research experience spans time series forecasting, salient object detection, and multi-UAV path planning and task allocation. I am currently working on AI-generated image detection with Assoc Prof Robby Tan from Yale-NUS College.I am particularly interested in developing robust and efficient learning-based methods for complex and dynamic environments.
Curriculum Vitae
Education
  • ShenZhen University
    ShenZhen University
    B.Eng. in Electronics and Information Engineering
    Sep. 2022 - Jul. 2026
  • National University of Singapore
    National University of Singapore
    M.Sc. in Electrical and Computer Engineering
    Aug. 2026 - JUL. 2027
Honors & Awards
  • Chinese Mathematics Competition, Third Prize
    2024
  • Greater Bay Area Data Application and Innovation Competition, Third Prize
    2024
  • Shenzhen University First-Class Academic Scholarship (Top 1%)
    2024
  • Shenzhen University Second-Class Academic Scholarship (Top 3%)
    2025 & 2023
  • Shenzhen University Second-Class Innovation and Entrepreneurship Scholarship (Top 3%)
    2025
  • Shenzhen University Outstanding Graduate & Bachelor's Degree with Honours
    2026
Internships
  • Research Assistant Intern
    The Smart City Research Institute of China Electronics Technology Corporation
    Research Assistant Intern
    Shenzhen, China
    Nov 2024 - May 2025
    • Optimized table recognition model using YOLO, OpenCV, and OCR; performed table detection, region cropping, structural parsing, cell extraction, and text recognition, converting image-based tables into editable files and reducing manual data entry.
    • Developed a financial data QA system by cleaning and standardizing historical financial data and importing it into a MySQL relational database. Implemented a rule- and BERT-based approach for user query intent classification and key entity extraction, mapping parsed queries to SQL templates for database retrieval and converting results into natural language responses.
    • Engineered an LLM-based intelligent security situational awareness system by performing deep semantic analysis and intent recognition on cross-domain heterogeneous logs. Designed expert-level prompt engineering and few-shot learning strategies to address security identification and real-time response challenges in complex scenarios.
Selected Publications (view all )
Graph-Based Uncertainty Modeling and Multimodal Fusion for Salient Object Detection
Graph-Based Uncertainty Modeling and Multimodal Fusion for Salient Object Detection

Yuqi Xiong, Wuzhen Shi, Yang Wen, Ruhan Liu

International Conference on Neural Information Processing (ICONIP) 2025

This project focuses on salient object detection in complex scenes, where we developed a dynamic uncertainty-aware graph convolution module to enhance the detection of fine structures and edge regions, addressing detail loss and blurred boundaries. We further designed a multimodal fusion strategy to adaptively integrate RGB, depth, and edge features, enabling cross-modal semantic complementarity and consistency. Experiments on standard datasets demonstrated improved edge clarity and robustness against complex backgrounds.

[Paper] [Code]

Graph-Based Uncertainty Modeling and Multimodal Fusion for Salient Object Detection

Yuqi Xiong, Wuzhen Shi, Yang Wen, Ruhan Liu

International Conference on Neural Information Processing (ICONIP) 2025

This project focuses on salient object detection in complex scenes, where we developed a dynamic uncertainty-aware graph convolution module to enhance the detection of fine structures and edge regions, addressing detail loss and blurred boundaries. We further designed a multimodal fusion strategy to adaptively integrate RGB, depth, and edge features, enabling cross-modal semantic complementarity and consistency. Experiments on standard datasets demonstrated improved edge clarity and robustness against complex backgrounds.

[Paper] [Code]

Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism
Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism

Yuqi Xiong, Yang Wen

International Joint Conference on Neural Networks (IJCNN) 2025

Proposed AEFIN, a novel framework for non-stationary time series forecasting that combines Fourier Transform-based decomposition to separate stationary and non-stationary components, cross-attention mechanisms for enhanced information sharing, and Fourier analysis for capturing periodic patterns. Designed a custom loss function that integrates MSE and MAE across time- and frequency-domain components to improve model robustness. The proposed framework achieved SOTA performance on most benchmark datasets, consistently improving MSE and MAE when integrated with mainstream Transformer- and CNN-based forecasting models.

[Paper] [Code]

Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism

Yuqi Xiong, Yang Wen

International Joint Conference on Neural Networks (IJCNN) 2025

Proposed AEFIN, a novel framework for non-stationary time series forecasting that combines Fourier Transform-based decomposition to separate stationary and non-stationary components, cross-attention mechanisms for enhanced information sharing, and Fourier analysis for capturing periodic patterns. Designed a custom loss function that integrates MSE and MAE across time- and frequency-domain components to improve model robustness. The proposed framework achieved SOTA performance on most benchmark datasets, consistently improving MSE and MAE when integrated with mainstream Transformer- and CNN-based forecasting models.

[Paper] [Code]

All publications