Hi, I'm a Computer Science and Design graduate from SUTD (Singapore University of Technology and Design). I’ve got a strong interest in today’s AI technologies, which led me to take up AI-focused courses and build real-world AI applications and solutions.
I’m also someone who’s open to new and unfamiliar environments, and I’m always looking for ways to grow and keep improving in any way, not only in tech.
Our team was tasked to develop a video captioning system that can generate captions for military scenarios. The system should be able generate detailed captions that describe the actions and events taking place in the video. The system should also be able to generate captions that are relevant to the military context, such as identifying specific objects, actions, and events that are relevant to military operations. We were also tasked to ensure that the system is able to generate captions in real-time, so that it can be used in live military operations. We named our final model DeepSub, a fine-tuned vision transformer model with InternVL2 as the base open source model. With our evaluation, our new model has achieved about 4x improvement in military object specificity when generating captions.
More Details
Our team partnered with a client promoting interfaith, interracial, and intercultural education to support trainers facing burnout from answering repetitive, sensitive questions. We developed an AI-powered web app that combines a curated FAQ system with a real-time chatbot, designed to handle complex topics respectfully and in line with the client’s values.
The platform supports session-based customization, letting trainers tailor content and control access. A human-in-the-loop feedback system allows flagged responses to be reviewed and reused for few-shot training, enabling continuous improvement of the chatbot over time.
More Details
Designed and implemented an LSTM-based deep learning model in PyTorch to predict the next-day closing price of Bitcoin. The model uses 10+ years of historical data with engineered time-based features like day of the week and month. Achieved a test MAPE of ~2.48% and RMSE of ~$2519.98, demonstrating solid short-term forecasting capability for financial time series.
More Details
A custom-built AI chatbot interface designed to enhance the documentation and learning experience. This project integrates features such as folder management, search, colored-tag filtering, and a prompt library system to streamline user workflows.
More Details
