3 papers
cs.LG2026
CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search
Cheonjun Park
Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs b…
cs.CV2026
ToaSt: Token Channel Selection and Structured Pruning for Efficient ViT
Hyunchan Moon, Cheonjun Park, Steven L. Waslander
Vision Transformers (ViTs) have achieved remarkable success across various vision tasks, yet their deployment is often hindered by prohibitive computational costs. While structured…
cs.CV2024
REPrune: Channel Pruning via Kernel Representative Selection
Mincheol Park, Dongjin Kim, Cheonjun Park +4
Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose s…