|
Jason Yoo I am a fourth-year Computer Science PhD student at the University of British Columbia advised by Dr. Frank Wood. Previously, I interned at Amazon Science and completed my BSc in Computer Science at the University of British Columbia. My research focuses on neural network continual learning, associative memories, and automated machine learning. Email / Google Scholar / Github / Linkedin |
|
Refereed Publications |
|
Lifelong Learning of Video Diffusion Models From a Single Video Stream
Jason Yoo, Yingchen He, Saeid Naderiparizi, Dylan Green, Gido M. van de Ven, Geoff Pleiss, Frank Wood arXiv preprint, 2024 [Paper] We show that training autoregressive video diffusion models from a single, continuous video stream can be competitive with offline training given the same number of gradient steps and introduce three new datasets. |
|
Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
Jason Yoo, Yunpeng Liu, Frank Wood, Geoff Pleiss ICML 2024 [Paper] We show that optimizing the experience replay loss in a way that stabilizes neural network representations between parameter updates improves online continual learning performance. |
|
BayesPCN: A Continually Learnable Predictive Coding Associative Memory
Jason Yoo, Frank Wood NeurIPS 2022 [Paper] [Blog] We continually learn a deep associative memory using predictive coding and locally conjugate Bayesian updates without meta-learning. |
|
Ensemble Squared: A Meta AutoML System
Jason Yoo, Tony Joseph, Dylan Yung, S. Ali Nasseri, Frank Wood arXiv preprint, 2020 [Paper] We ensemble the state-of-the-art AutoML systems to exploit the diversity in their model search space and heuristics. |
AI Reading ListThis is a list of books on intelligence that I have enjoyed or am enjoying in no particular order. Textbooks are not included. Finished
In Progress
|