<p>Teaching foundation models new skills without breaking them is hard. A new reinforcement learning-based approach might have the power to change that.</p>
<p>The post <a href="https://towardsdatascience.com/could-on-policy-self-distillation-revolutionize-post-training/">Could On-Policy Self-Distillation Revolutionize Post-Training?</a> appeared first on <a href="https://towardsdatascience.com">Towards Data Science</a>.</p>