Sign up to save your podcasts
Or
Share ScaleRL by Meta: Making AI Training Predictable
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
ScaleRL by Meta: Making AI Training Predictable
Researchers at Meta developed "ScaleRL," a groundbreaking recipe that makes LLM reinforcement learning training predictable, just like pre-training.
Paper: https://arxiv.org/pdf/2510.13786
Hear it broken down simply on the GenAI Learner podcast.
View all episodes
By hogarthian.artResearchers at Meta developed "ScaleRL," a groundbreaking recipe that makes LLM reinforcement learning training predictable, just like pre-training.
Paper: https://arxiv.org/pdf/2510.13786
Hear it broken down simply on the GenAI Learner podcast.