@misc{chu2025memorizes, title={SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training}, author={Tianzhe Chu and Yuexiang Zhai and Jihan Yang and Shengbang Tong and Saining Xie and Dale Schuurmans and Quoc V. Le and Sergey Levine and Yi Ma}, year={2025}, eprint={2501.17161}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2501.17161} }