cover of episode 711: Image, Video and 3D-Model Generation from Natural Language, with Dr. Ajay Jain

711: Image, Video and 3D-Model Generation from Natural Language, with Dr. Ajay Jain

2023/9/5
logo of podcast Super Data Science: ML & AI Podcast with Jon Krohn

Super Data Science: ML & AI Podcast with Jon Krohn

Frequently requested episodes will be transcribed first

Shownotes Transcript

In this episode, host Jon Krohn explores with his guest Ajay Jain, Co-Founder of Genmo.ai, how creative general intelligence could take the video industry by storm. They also discuss the models that got Genmo to this point, the applications of NeRF, and how understanding human psychology is so essential to developing models that output high-fidelity video.This episode is brought to you by the Zerve) data science dev environment, by Grafbase), the unified data layer, and by Modelbit), for deploying models in seconds. Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast) for sponsorship information.In this episode you will learn:• About Genmo.ai and the term “creative general intelligence” [03:47]• Why Ajay started Genmo.ai [09:26]• The increased performance of multimodal models [21:12]• All about Denoising Diffusion Probabilistic Models (DDPMs) [31:03]• The application of Neural Radiance Fields (NeRF) [55:26]• Predicting pedestrian behavior at Uber [1:01:50]• How to save money in the process of training models [1:12:42]Additional materials: www.superdatascience.com/711)