Kwanhee Lee
kwanhee
AI & ML interests
Model compression, optimization
Recent Activity
upvoted a paper about 2 hours ago
Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts upvoted a collection about 2 hours ago
MoESQ authored a paper 1 day ago
The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM