The Pacific Laboratory for Artificial Intelligence (PLAI)
Welcome to PLAI, a cutting-edge research group based in the Department of Computer Science at the University of British Columbia. Our mission is to advance the frontiers of artificial intelligence through groundbreaking work in generative modelling, reinforcement learning, probabilistic programming, and Bayesian inference. At our core, we are driven by a vision to ensure safe and reliable generative AI that humanity can trust. We aim to build systems that not only push technical boundaries but also make a lasting positive impact on society.
The Pacific Laboratory for Artificial Intelligence (PLAI) was founded by Professor Frank Wood in 2018 after his move from Oxford to UBC.
Recent Research BLOG
- Lifelong Learning of Video Diffusion Models From a Single Video StreamPLAI group member Jason Yoo and colleagues, under the supervision of Dr. Frank Wood and Dr. Geoff Pleiss, have released a new paper on training autoregressive video diffusion models from a continuous video stream that outputs one video frame at a time. The AI community has long sought models and algorithms that learn… Read more: Lifelong Learning of Video Diffusion Models From a Single Video Stream
- plaicraft.ai launchWe are proud to announce that UBC’s Behavioral Research Ethics Board has issued a certificate of approval under the minimal risk category for us to publicly release plaicraft.ai, a “free Minecraft in the cloud” generative AI research data collection project. Please consider contributing by signing up and playing Minecraft in your browser at… Read more: plaicraft.ai launch
- Visual Chain-of-Thought Diffusion ModelsImages generated by our baseline, EDM. They mostly look realistic but there are occasionally artifacts – see the blobs on the chin in the first and seventh images. Images generated by our method. We don’t see any of the artifacts that were present in images from the baseline. At this year’s CVPR workshop… Read more: Visual Chain-of-Thought Diffusion Models
- Graphically Structured Diffusion ModelsChristian Weilbach and Will Harvey, under the supervision of Dr. Frank Wood (PLAI group), have just released a paper on a new deep generative framework to learn structured diffusion models. In contrast to our approach, picture a traditional algorithm design that requires careful mathematical reasoning and a precise implementation in light of numerical… Read more: Graphically Structured Diffusion Models
- Continually Learning Deep Associative MemoriesAssociative memories are models that store and recall patterns. Pattern recall (associative recall) is a process whereby an associative memory, upon receiving a potentially corrupted memory query, retrieves the associated value from memory. Pattern storage is a process whereby an associative memory adjusts its parameters such that the new pattern can be recalled… Read more: Continually Learning Deep Associative Memories