Marcin Chochowski

Researcher, NVIDIA

Joined

February 2024

Names

Marcin Chochowski (Preferred)

Emails

****@nvidia.com (Confirmed)

,

****@gmail.com

Personal Links

Career & Education History

Researcher

NVIDIA (nvidia.com)

2021 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Scaling Fine-Grained MoE Beyond 50B Parameters: Empirical Evaluation and Practical Insights
Jakub Krajewski, Marcin Chochowski, Daniel Korzekwa
- ES-FoMo III
- Readers: Everyone
Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Marcin Chochowski, Yashaswi Karnati, Raviraj Bhuminand Joshi, Ameya Sunil Mahabaleshwarkar, ZIJIA CHEN, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, Jan Kautz, Bryan Catanzaro, Ashwath Aithal, Nima Tajbakhsh, Pavlo Molchanov
- NeurIPS 2025 poster
- Readers: Everyone
LLM Pruning and Distillation in Practice
Sharath Turuvekere Sreenivas, Saurav Muralidharan, Raviraj Bhuminand Joshi, Marcin Chochowski, Mostofa Patwary, Pavlo Molchanov, Mohammad Shoeybi, Jan Kautz, Ameya Sunil Mahabaleshwarkar, Gerald Shen, Jiaqi Zeng, Oleksii Kuchaiev, ZIJIA CHEN, Yoshi Suhara, Shizhe Diao, Chenhan D. Yu, Wei-Chun Chen, Hayley Ross, Daniel Korzekwa, Oluwatobi Olabiyi et al. (2 additional authors not shown)
- Submitted to ICLR 2025
- Readers: Everyone
Compact Language Models via Pruning and Knowledge Distillation
Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Bhuminand Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov
- NeurIPS 2024 poster
- Readers: Everyone
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
Piotr Nawrot, Adrian Łańcucki, Marcin Chochowski, David Tarjan, Edoardo Ponti
- ICML 2024 Poster
- Readers: Everyone

Co-Authors

View all 29 co-authors