Shuchang Ye

Shuchang Ye

Multimodal Learning Researcher at The University of Sydney

Shuchang Ye

Education

The University of Sydney – Sydney, Australia
Doctor of Philosophy (Engineering) in Multimodal Learning
Mar 2024 - Present

  • Honours and Awards: Full Government RTP Scholarship.

The University of Sydney – Sydney, Australia
Bachelor of Advanced Computing (Honours) in Computer Science and Computational Data Science
Mar 2020 - Jan 2024

  • GPA: 3.91/4.00 (top 1%), Honour First Class
  • Honours and Awards: Ian Jackson Memorial Prize for Computer Science, Dalyell Scholar, Dean List

Skills

  • Programming Languages: Python, Java, C, C#, C++
  • Deep Learning Frameworks: PyTorch, TensorFlow, Huggingface, JAX
  • Fundamental Deep Learning: Representation Learning, Self-supervised Learning, Weakly-supervised Learning, Knowledge Distillation
  • Multimodal Learning: Hallucination, Bias and Fairness, Catastrophic Forgetting, Alignment, Pre-training, Fine-tuning, Adaptation
  • Computer Vision and Pattern Recognition: Object Detection, Semantic Segmentation, Image Classification, Image Generation, Visual Question Answering, Image Captioning, Masked Image Modeling, Face Recognition
  • Natural Language Processing: Masked Language Modeling, Text Classification, Text Generation, Question Answering, Named Entity Recognition
  • Web Development: HTML, CSS, JavaScript, Django, Flask, SQL, Node.js
  • Data Science: R, RStudio, Jupyter Notebook, MATLAB

Patents and Publications C=Conference, J=Journal, P=Patent, S=In Submission, T=Thesis

  1. [S.1] Shuchang Ye, Mingyuan Meng, Mingjian Li, Dagan Feng, Usman Naseem, Jinman Kim. Dynamic Traceback Learning for Medical Report Generation. Manuscript submitted for review in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025). arXiv

  2. [C.2] Shuchang Ye, Usman Naseem, Mingyuan Meng, Dagan Feng, Jinman Kim. A Causal Approach to Mitigate Modality Preference Bias in Medical Visual Question Answering. In The 32nd ACM International Conference on Multimedia (ACM MM 2024) First International Workshop on Vision-Language Models for Biomedical Applications: VLM4Bio 2024, ACM ISBN 979-8-4007-1207-4/24/10, DOI: 10.1145/3689096.3689459.

  3. [C.1] Shuchang Ye, Mingyuan Meng, Mingjian Li, Dagan Feng, Jinman Kim. Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance. In The 27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024). arXiv Website GitHub

Experience

The University of Sydney – Sydney, Australia
Research Assistant
Jul 2022 - Dec 2022

  • Research in Facial Recognition, available at PDF
  • Keywords: Computer Vision, Object Detection, Convolutional neural network

Projects

Brain Wave Intelligent Reader
Tools: Python, R, HTML, SQL, CSS, JavaScript, Spiker Box
Feb 2022 - Jun 2022

  • Project Background: Utilizing a Spikerbox device, capable of recording brainwave activity, we classify various eye movements such as leftward and rightward shifts, as well as blinks. The objective of this project is to develop an intelligent e-book that autonomously turns pages and adjusts line spacing in response to the reader’s behavior.
  • Key components: 1) Deep learning-based streaming brain wave long sequence predictor; 2) Development of intelligent book reader.