Continuous Learning Methods
Kelvin discusses the challenges of updating model weights in real time and the benefits of continuous learning methods like prompt tuning. He also delves into the concept of training data attribution, highlighting the complexities faced by large language models in understanding the source of their knowledge.In this clip
From this podcast
No Priors
No Priors Ep. 15 | With Kelvin Guu, Staff Research Scientist, Google Brain
Related Questions