Maryam Mehri Dehnavi

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs

OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction

SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs

SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression

SLiM: One-shot Quantized Sparse Plus Low-rank Approximation of LLMs