Lossy and Lossless (L$^2$) Post-training Model Size Compression

Lossy and Lossless (L $^2$ ) Post-training Model Size Compression

IEEE International Conference on Computer Vision (ICCV), 2023

8 August 2023

ArXiv (abs)PDF HTML Github (13★)

Papers citing "Lossy and Lossless (L$^2$) Post-training Model Size Compression"

3 / 3 papers shown

Title
BitSnap: Checkpoint Sparsification and Quantization in LLM Training Yanxin Peng Qingping Li Baodong Wu Shigang Li Guohao Dai Shengen Yan Yu Wang MQ 265 0 0 15 Nov 2025
Flexible Mixed Precision Quantization for Learned Image CompressionIEEE International Conference on Multimedia and Expo (ICME), 2024 Md Adnan Faisal Hossain Z. Duan Fengqing Zhu MQ 172 1 0 02 Jun 2025
TinySeg: Model Optimizing Framework for Image Segmentation on Tiny Embedded SystemsACM SIGPLAN Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES), 2024 Byungchul Chae Jiae Kim Seonyeong Heo VLM 153 2 0 03 May 2024