@article{efficienthybridlanguagemodelcompression,
  title = {Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning},
  author = {Ali Taghibakhshi and Sharath Turuvekere Sreenivas and Saurav Muralidharan and Marcin Chochowski and Yashaswi Karnati and Raviraj Joshi and Ameya Sunil Mahabaleshwarkar and Zijia Chen and Yoshi Suhara and Oluwatobi Olabiyi and Daniel Korzekwa and Mostofa Patwary and Mohammad Shoeybi and Jan Kautz and Bryan Catanzaro and Ashwath Aithal and Nima Tajbakhsh and Pavlo Molchanov},
  year = {2025},
  eprint = {2504.11409},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.11409v1},
}