AIConfPaper
← Search

Saurav Muralidharan

6 accepted papers

2026

Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control

Ali Taghibakhshi, Ruisi Cai, Saurav Muralidharan, Sharath Turuvekere Sreenivas, Ameya Mahabaleshwarkar, Marcin Chochowski +10
ICML 2026poster

Training a family of large language models (LLMs), either from scratch or via iterative compression, is prohibitively expensive and inefficient, requiring separate training runs for each model in the family. In this paper, we introduce Star Elastic, a novel LLM post-training method that adds N neste…

Cited by 0Source ↗Scholar ↗
2025

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Marcin Chochowski, Yashaswi Karnati, Raviraj Bhuminand Joshi +12
NeurIPS 2025poster

Hybrid language models that combine Attention and State Space Models (SSMs) have been shown to achieve state-of-the-art accuracy and runtime performance. Recent work has also demonstrated that applying pruning and distillation to Attention-only models yields smaller, more accurate models at a fracti…

Cited by 0Source ↗Scholar ↗
2025

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

Ruisi Cai, Saurav Muralidharan, Hongxu Yin, Zhangyang Wang, Jan Kautz, Pavlo Molchanov
ICLR 2025poster

Large Language Model (LLM) providers typically train a family of models, each of a different size targeting a specific deployment scenario. Models in the family are all trained from scratch, making the process extremely resource intensive. Recent work has successfully reduced the cost of training mo…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Compact Language Models via Pruning and Knowledge Distillation

Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Bhuminand Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi +3
NeurIPS 2024poster

Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In this paper, we investigate if pruning an existing LLM and then re-training it with a fraction <3% of the original trainin…

Cited by 66Source ↗PDF ↗code ↗Scholar ↗
2024

Flextron: Many-in-One Flexible Large Language Model

Ruisi Cai, Saurav Muralidharan, Greg Heinrich, Hongxu Yin, Zhangyang Wang, Jan Kautz +1
ICML 2024oral

Training modern LLMs is extremely resource intensive, and customizing them for various deployment scenarios characterized by limited compute and memory resources through repeated training is impractical. In this paper, we introduce Flextron, a network architecture and post-training model optimizatio…

Cited by 16Source ↗PDF ↗Scholar ↗
2024

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

Gongfan Fang, Hongxu Yin, Saurav Muralidharan, Greg Heinrich, Jeff Pool, Jan Kautz +2
NeurIPS 2024spotlight

Large Language Models (LLMs) are distinguished by their massive parameter counts, which typically result in significant redundancy. This work introduces MaskLLM, a learnable pruning method that establishes Semi-structured (or ``N:M'') Sparsity in LLMs, aimed at reducing computational overhead during…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗