Training Large Language Models with RLHF
Introduction Generative AI has seen remarkable advancements across domains like image, video, and text generation. This blog explores how diffusion models and variational autoencoders (VAEs) contr...
Simon Ryu
Training Large Language Models with RLHF
Introduction Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for fine-tuning Large Language Models (LLMs), enabling them to align more closely with human pref...
Automating Golf Swing Detection and Analysis
Automating Golf Swing Analysis with Computer Vision and Machine Learning The source coode for the application is hosted on GitHub, found here. As an avid golfer and machine learning enthusias...
Building an advanced Golf Instruction Chatbot
The source code is hosted on GitHub, found here. As a software engineer with a passion for both AI and golf, I recently completed a project that combines these interests in an exciting way. I dev...
Developing an Augmented Reality Menu Application for Group Dining
The source code for the application is hosted on GitHub, found here. Application demo As part of my Engineering Physics project at the University of British Columbia, I worked with my tea...
Transferring DynamoDB data between environments
This packaging distribution is published on PyPI, found here. The source code is hosted on GitHub, found here. Introduction Maintaining multiple environments can be hard, especially on a cloud-ba...
Building an Autonomous License Plate Reading Robot
The source code for CNN training pipeline is hosted on GitHub, found here. As part of our ENPH 353 course at UBC, my team and I tackled an exciting challenge: creating an autonomous robot capable...