I'm a final-year Artificial Intelligence student from Ho Chi Minh City with a strong passion for building impactful AI/ML solutions. I specialize in Deep Learning, Computer Vision, and Natural Language Processing. I enjoy tackling real-world problems and turning complex data into actionable insights.
I'm constantly exploring new challenges and honing my skills. Currently, my focus is on:
- π End-to-End Application Development: Applying prompt engineering techniques and working with LLM APIs (like Google Gemini) to create user-friendly tools like my Better Prompt Chrome Extension.
- π― Fine-tuning Vision-Language Models (VLMs): Adapting models like Gemma-3 using parameter-efficient techniques (LoRA/PEFT) and 4-bit quantization to build practical, on-device AI solutions for tasks like visual Q&A.
- πΉ Spatiotemporal Video Analysis: Building robust deep learning pipelines, such as Two-Stream 3D CNNs, to understand and classify complex events in videos, like in my Video Violence Detection project.
- π΅ Multi-Label Audio Classification: Developing and optimizing deep learning systems to recognize multiple sound events simultaneously, tackling challenges like the BirdCLEF 2025 competition.
β The best way to predict the future is to create it. β
