ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation.

Zhiyu Mei Wei Fu Kaiwei Li Guangju Wang Huanchen Zhang Yi Wu 0013 ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation. 2025 MLSys https://openreview.net/forum?id=yLU1zRf95d https://proceedings.mlsys.org/paper_files/paper/2025/hash/3b3889d313ba9476c12c2d77ea66b24f-Abstract-Conference.html conf/mlsys/2025 db/conf/mlsys/mlsys2025.html#MeiFLWZ025