Saurav Muralidharan  

 



  ![](/sites/default/files/person/Saurav.jpg)

  

 Saurav Muralidharan is a Senior Research Scientist in the [Deep Learning Efficiency Research (DLER)](https://nv-dler.github.io/) team. He specializes in LLM efficiency and performance optimization and has worked on model compression (pruning, distillation, low-rank factorization), SLMs, elastic and mixture-of-expert (MoE) networks. Please visit [sauravm.com](https://www.sauravm.com) for more details on his research.



   Research Area(s)

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Generative AI](/research-area/generative-ai)

[High Performance Computing](/research-area/high-performance-computing)

 

 

  

 Main Field of Interest

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

 

  

 

 

 



 ### Publications

 

### 2025 

[Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning](/publication/2025-04_minitron-ssm-efficient-hybrid-language-model-compression-through-group-aware)

Ali Taghibakhshi, Sharath Turuvekere Sreenivas, [Saurav Muralidharan](/person/saurav-muralidharan), Marcin Chochowski, Yashaswi Karnati, Raviraj Joshi, Ameya Sunil Mahabaleshwarkar, Zijia Chen, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, [Jan Kautz](/person/jan-kautz), Bryan Catanzaro, Ashwath Aithal, Nima Tajbakhsh, [Pavlo Molchanov](/person/pavlo-molchanov)



[NeurIPS 2025](https://arxiv.org/abs/2504.11409)









### 2024 

[LLM Pruning and Distillation in Practice: The Minitron Approach](/publication/2024-08_llm-pruning-and-distillation-practice-minitron-approach)

Sharath Turuvekere Sreenivas, [Saurav Muralidharan](/person/saurav-muralidharan), Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, [Jan Kautz](/person/jan-kautz), [Pavlo Molchanov](/person/pavlo-molchanov)













### 2020 

[A Programmable Approach to Neural Network Compression](/publication/2020-10_programmable-approach-neural-network-compression)

Vinu Joseph, Ganesh L. Gopalakrishnan, [Saurav Muralidharan](/person/saurav-muralidharan), [Michael Garland](/person/michael-garland), Animesh Garg



[IEEE Micro: Special Issue on Machine Learning for Systems](https://ieeexplore.ieee.org/document/9151283)