Poster "training-free compression" Papers
2 papers found
Conference
BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
Xinghao Wang, Pengyu Wang, Bo Wang et al.
ICLR 2025arXiv:2410.23918
7
citations
PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference
Tanvir Mahmud, Burhaneddin Yaman, Chun-Hao Liu et al.
ECCV 2024arXiv:2403.16020
7
citations