GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism

Access the preprint.

Recommended citation: Chen Tang, Bo Lv, Zifan Zheng, Bohao Yang, Kun Zhao, Ning Liao, Xiaoxing Wang, Feiyu Xiong, Zhiyu Li, Nayu Liu, Jingchi Jiang, "GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism." arXiv:2501.07890, 2025.
Download Paper