English Version | 中文版

I am currently a senior AI major student at TamKang University in Taiwan. My primary focus is in computer vision, image processing, artificial intelligence, machine learning, and natural language processing (NLP). I have a passion for developing AI models, especially in areas like semantic segmentation and computer vision.

I am also actively involved in AI research and am constantly exploring ways to apply AI in practical scenarios. I have recently applied for the pre-research student qualification in my department and am looking for opportunities to collaborate with professors on cutting-edge AI projects.

• Programming Languages: Python, C
• AI/ML Frameworks: PyTorch, TensorRT, TensorFlow
• Natural Language Processing: BERT, GPT, Transformer-based models
• Data Science: NumPy, Pandas, Matplotlib, scikit-learn
• Other Tools: Git, Docker, Linux, Jupyter Notebook

• Interactive video segmentation: To achieve real-time interactive effects, this research integrates language input with real-time interactive image segmentation. Current image segmentation methods primarily rely on manual selection, and due to the large size and complexity of language models, they are not suitable for edge device applications. This study proposes using a smaller language model to enable efficient execution of the task on edge devices.
• Video Object Segmentation (REFVOS): Refining models to handle real-time video data, ensuring more precise segmentation and tracking based on textual input.
• Sewer System Analysis: Working on implementing machine learning techniques to automate the detection of anomalies in sewer systems, enhancing infrastructure maintenance efficiency.

• Model Optimization: Focusing on optimizing AI models for deployment using TensorRT and other performance-enhancing tools.
• Advanced Deep Learning Techniques: Continuously learning about new architectures, optimization algorithms, and frameworks.

• Email: [email protected]
• LinkedIn: https://www.linkedin.com/in/melvin0kuo/
• GitHub: https://github.com/melvin0kuo

Feel free to reach out if you’re interested in collaborating or just want to chat about AI and machine learning!

English Version | 中文版

我目前是淡江大學的人工智慧學系四年級學生，專攻電腦視覺、影像處理、人工智慧、機器學習以及自然語言處理（NLP）。我對開發AI模型充滿熱情，尤其是在語意分割及電腦視覺領域。

我積極參與AI研究，並不斷探索如何將AI應用於實際情境中。我最近申請了系上的預研資格，並尋找機會與教授合作進行前沿的AI專案。

• 程式語言：Python, C
• AI/ML 框架：PyTorch, TensorRT, TensorFlow
• 自然語言處理：BERT, GPT, 基於Transformer的模型
• 資料科學：NumPy, Pandas, Matplotlib, scikit-learn
• 其他工具：Git, Docker, Linux, Jupyter Notebook

• 互動式影像分割：結合語言輸入，實現即時互動的影像分割，以達到即時互動的效果。目前的影像分割方法主要依賴手動選取，且由於語言模型過大和複雜，不利於邊緣設備的應用。本研究提出使用較小的語言模型，使邊緣設備能夠高效執行該任務。
• 利用人工智慧AI辨識污水管內異常之可行性研究：應用機器學習技術，自動化檢測下水道中的異常情況，以提升基礎設施維護效率。

• 模型優化：專注於使用TensorRT和其他工具來優化AI模型的部署效能。
• 先進的深度學習技術：持續學習新架構、優化算法和框架。

• 電子郵件: [email protected]
• LinkedIn: https://www.linkedin.com/in/melvin0kuo/
• GitHub: https://github.com/melvin0kuo

除了寫程式外，我喜歡探索電腦軟硬體,擁有淡江大學電腦維修隊中級維修證照,正在朝著高級維修證照努力中。

成績較好的科目

如果你對AI專案或合作有興趣，或只是想聊聊人工智慧和機器學習，歡迎聯繫我！