Completed
- Creating a shared latent space w/ Vector Quantization
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
NÜWA - Visual Synthesis Pre-training for Neural Visual World Creation
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro & Outline
- 2 - Sponsor: ClearML
- 3 - Tasks & Naming
- 4 - The problem with recurrent image generation
- 5 - Creating a shared latent space w/ Vector Quantization
- 6 - Transforming the latent representation
- 7 - Recap: Self- and Cross-Attention
- 8 - 3D Nearby Self-Attention
- 9 - Pre-Training Objective
- 10 - Experimental Results
- 11 - Conclusion & Comments
