Imbalanced Gradients in RL Post-Training of Multi-Task LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Runzhe, Samanta, Ankur, Jain, Ayush, Fujimoto, Scott, Kwon, Jeongyeol, Kretzu, Ben, Yu, Youliang, Hassani, Kaveh, Vidolov, Boris, Efroni, Yonathan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.19178