Hugging Face Journal Club: Joint Scaling Laws for Pre-training & RL

Hugging Face · youtube · 2026-08-04

The Hugging Face research team discussed the paper "Understanding Reasoning from Pretraining to Post-Training" during their Journal Club session.

The research proposes a joint scaling law for pre-training and reinforcement learning. The discussion focuses on how these joint scaling laws operate across different training stages, offering a new perspective on understanding the emergence of reasoning capabilities in large models.

Original post →

More from Research

Research channel →