This article explores a method to stabilize generative models using synthetic data.
― 5 min read
Calvin Luo
TADPoLe trains agents using text-based rewards for natural task execution.
― 7 min read
Cutting edge science explained simply
This article explores a method to stabilize generative models using synthetic data.
― 5 min read
TADPoLe trains agents using text-based rewards for natural task execution.
― 7 min read