DailyPapers
@HuggingPapers
Tweeting interesting papers submitted at
Submit your own at and link models/datasets/demos to it!
加入 March 2025
4 正在關注 21.6K 粉絲
Understanding Reasoning from Pretraining to Post-Training
A controlled study using chess to show that pretraining loss predicts post-RL performance and that RL discovers new correct moves on hard puzzles.
顯示更多
