0:00-53:23
Streams straight from the publisher. podnod never proxies or re-hosts episode audio.
Todays paper: data2vec (https://arxiv.org/abs/2202.03555)
Summary of the paper
A multimodal SSL algorithm that predicts latent representation of different types of input.
Highlights of discussion
- What are the motivations of SSL and multimodal
- How does the student teacher learning work?
- What are similarities and differences between ViT, BYOL, and Reinforcement Learning algorithms.
No links were found in this episode’s notes.