Compressing Large Language Models by Joint Sparsification and Quantization

Jinyang Guo, Jianyu Wu, Zining Wang, Jiaheng Liu, Ge Yang +4 more
2/12/2026

No official code found. Best implementation: uanu2002/JSQ (124 stars, MIT, last commit 2024-10-24).

Semantic Scholar

Code Implementations(1)

uanu2002/JSQCommunity71%
MIT

[ICML 2024] JSQ: Compressing Large Language Models by Joint Sparsification and Quantization

1243PythonMay 23, 20241 years agoMIT

Similar Papers

Finding Generalization Measures by Contrasting Signal and Noise

100% match2026

Improving Non-Transferable Representation Learning by Harnessing Content and Style

96% match2026

Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal Consistency

96% match1 repo142026

High-Fidelity 3D Textured Shapes Generation by Sparse Encoding and Adversarial Decoding

95% match1 repo52026

CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation

95% match2026

Improving Differentiable Neural Architecture Search by Encouraging Transferability

93% match2026

Cite this paper

@article{guo2026compressing,
  title  = {Compressing Large Language Models by Joint Sparsification and Quantization},
  author = {Jinyang Guo and Jianyu Wu and Zining Wang and Jiaheng Liu and Ge Yang and Yifu Ding and Ruihao Gong and Haotong Qin and Xianglong Liu},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:346714f374346f7afa82eb8ff50698b72feada6d},
  journal = {ICML 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/346714f374346f7afa82eb8ff50698b72feada6d.svg)](https://codeofpaper.com/paper/346714f374346f7afa82eb8ff50698b72feada6d)

Discussion