Author

Jixian Zhou

Observed name: Zhou, Jixian

OpenAlex ID: A5124909024

Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers

2026 · Chen, Anrui, Huang, Ruijun, et al. · arXiv (Cornell University)

SD-MoE: Spectral Decomposition for Effective Expert Specialization

2026 · Huang, Ruijun, Dong, Fang, et al. · arXiv (Cornell University)

Dispelling the Curse of Singularities in Neural Network Optimizations

2026 · Cao, Hengjie, Chen, Mengyi, et al. · arXiv (Cornell University)

Works count: 3

Citation count:

H-index:

I10-index: