Highly accomplished Ph.D. Candidate in Computer Science with extensive research experience in advanced Machine Learning and Computer Vision, specializing in innovative applications for medical image analysis and multi-modal learning. Proven ability to develop state-of-the-art deep learning frameworks, evidenced by multiple peer-reviewed publications in top-tier conferences like CVPR, MICCAI, and AAAI, and significant contributions during internships at NVIDIA, Microsoft Research Asia, and Tencent AI Lab.
San Diego, CA, US
→
Summary
Orchestrated advanced machine learning and computer vision research, developing innovative solutions for medical image analysis and multi-modal learning that resulted in multiple top-tier publications.
Highlights
Developed novel multi-modal learning frameworks for medical image analysis, achieving state-of-the-art performance in chest X-ray and histopathology tasks.
Designed and implemented privacy-preserving federated learning approaches for distributed medical AI, improving data security and model robustness by X% (specific metric to be added if available).
Pioneered self-supervised learning techniques for robust feature extraction across diverse datasets, enhancing model generalization and reducing reliance on labeled data by Y%.
Authored and co-authored multiple peer-reviewed publications in top-tier conferences including CVPR, MICCAI, AAAI, and BMVC, advancing the state-of-the-art in AI research.
Santa Clara, CA, US
→
Summary
Developed and validated a novel multi-modal learning framework for chest X-ray analysis, achieving state-of-the-art performance and contributing to a MICCAI publication.
Highlights
Engineered a novel multi-modal learning framework for chest X-ray analysis, integrating clinical text with imaging data to improve diagnostic accuracy by up to 5%.
Implemented and optimized deep learning models in PyTorch, achieving state-of-the-art performance on public medical benchmarks within a 3-month internship.
Collaborated with a team of researchers to prepare and publish findings at MICCAI 2023, contributing to the advancement of medical AI technologies.
Beijing, Beijing, China
→
Summary
Conducted impactful research on self-supervised learning for multi-modal medical image segmentation, significantly enhancing model performance and data efficiency for an AAAI publication.
Highlights
Designed and implemented a novel self-supervised learning framework for multi-modal medical image segmentation, reducing annotation requirements by approximately 30%.
Achieved significant performance improvements in segmentation tasks, demonstrating enhanced robustness and generalization across diverse datasets.
Contributed to a research publication presented at AAAI 2023, showcasing innovative approaches to medical image analysis and self-supervised learning.
Shenzhen, Guangdong, China
→
Summary
Explored and implemented disentangled representation learning for medical image analysis, enhancing interpretability and diagnostic accuracy of AI models, leading to a BMVC publication.
Highlights
Developed a novel disentangled representation learning framework for medical image analysis, improving model interpretability and diagnostic accuracy by 7%.
Implemented deep learning models to effectively separate distinct explanatory factors in medical images, facilitating more precise analysis.
Contributed to a peer-reviewed publication at BMVC 2021, showcasing innovative research in explainable AI for healthcare applications.
Awarded By
University of California, San Diego
Awarded for outstanding academic excellence and research potential within the Computer Science and Engineering Ph.D. program.
Awarded By
University of California, San Diego
Recognized for exceptional academic achievement across multiple quarters during undergraduate studies.
Published by
MICCAI (Medical Image Computing and Computer Assisted Intervention)
Summary
Proposed a new multi-modal learning framework that effectively combines visual and textual information from chest X-rays to enhance diagnostic accuracy and clinical utility.
Published by
AAAI (Association for the Advancement of Artificial Intelligence)
Summary
Developed a novel self-supervised learning framework for multi-modal medical image segmentation, significantly reducing the need for manual annotations and improving model generalization.
Deep Learning, Computer Vision, Multi-modal Learning, Federated Learning, Self-supervised Learning, Explainable AI, Medical Image Analysis, Transfer Learning, Representation Learning, Generative Models, Uncertainty Quantification.
Python, C++, MATLAB.
PyTorch, TensorFlow, scikit-learn, OpenCV, NumPy, Pandas.
Git, LaTeX, Linux, Docker, Jupyter Notebook.
Scientific Writing, Data Analysis, Experimental Design, Model Evaluation, Literature Review, Statistical Analysis.