In this interview, I had the pleasure to converse with Jarrod Teo, a seasoned consultant data science leader, to delve into the intersection of data science and business strategy. Jarrod shares insights from his journey developing AI tools that propel business valuations, tackle data acquisition hurdles, and harness the power of large language models in …
Day: 15 February 2024
Video generation models as world simulators
We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of high fidelity video. Our results suggest that scaling video generation models is a promising path towards building general purpose simulators of the physical world.