Scholar
Saurav Muralidharan
Google Scholar ID: GXlChWcAAAAJ
NVIDIA
Citations & Impact
Citations
538
H-index
11
i10-index
11
Publications
20
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Published 'Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning' at NeurIPS 2025.
- Published 'LlamaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing' at ICLR 2025.
- Published 'Compact Language Models via Pruning and Knowledge Distillation' at NeurIPS 2024.
- Published 'MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models' at NeurIPS 2024 (Spotlight).
- Released 'LLM Pruning and Distillation in Practice: The Minitron Approach' on arXiv 2024.
- Published 'Flextron: Many-in-One Flexible Large Language Model' at ICML 2024 (Oral).
- Released 'HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity' on arXiv 2023.
- Published 'Uniform Sparsity in Deep Neural Networks' at MLSys 2023.
