SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
Paper
•
2506.18349
•
Published
•
8
Zichong Li
Pearush
·
AI & ML interests
None yet
Recent Activity
liked
a model
1 day ago
microsoft/Phi-tiny-MoE-instruct
authored
a paper
2 days ago
COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of
LLMs
authored
a paper
2 days ago
LLMs Can Generate a Better Answer by Aggregating Their Own Responses
Organizations
upvoted
2
papers
2 days ago