3 papers
cs.LG2026
3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs
Mehdi Makni, Xiang Meng, Rahul Mazumder
Sparse plus Low-Rank decomposition of Large Language Models (LLMs) has emerged as a promising direction in model compression, aiming to decompose pre-t…
cs.AI2025
Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction
Ryan Lucas, Kayhan Behdin, Zhipeng Wang +3
Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression t…
cs.LG2024
Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework
Ryan Lucas, Rahul Mazumder
We present SNOWS, a one-shot post-training pruning framework aimed at reducing the cost of vision network inference without retraining. Current leading one-shot pruning methods min…