Search papers, labs, and topics across Lattice.
Yuedong Xu is with College of Computer Science and Artificial Intelligence, and Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China (e-mail: ydxu@fudan.edu.cn)
1
0
3
0
By fusing orthogonalized momentum with adaptive noise scaling, NAMO and NAMO-D offer a surprisingly simple recipe for faster and more stable LLM training compared to AdamW and Muon.
