I'm a deep-learning researcher focused on multi-modal learning. My core interest lies in exploring how LLMs' language understanding can be integrated with other modalities, like vision, to unlock new possibilities.
- Core Focus: Multi-modal Learning, Visual Question Answering (VQA).
- Current Goal: Extending the reasoning capabilities of LLMs beyond the textual domain.
- Languages: Python (with a heavy focus on deep learning and data analysis).
- Tools & Libraries: PyTorch, Hugging Face Transformers, PEFT, Accelerate.
- Email: nguyenphucthinh106@gmail.com
