SS
Sharath Turuvekere Sreenivas
cs.CLcs.LGcs.AIcs.CVeess.IV
On Valency
published · living versionsW_4ky4pfju·v1 · currentpublished
CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer
with Mingyu Yang, Adithyakrishna Venkatesh Hanasoge, Nima Tajbakhsh, Ashwath Aithal +1
1 version
Preprints & journals
19 papers in the corpus · 2020–2026CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer2610.28895v1 · Mingyu Yang, Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge et al.2026 · 0 citationsarXivon Valency
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better2610.11291v1 · Siyan Zhao, Yonggan Fu, Jindong Jiang et al.2026 · 0 citationsarXiv
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding2607.05722v1 · Yonggan Fu, Lexington Whalen, Abhinav Garg et al.2026 · 0 citationsarXiv
Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs2607.04371v2 · Akhiad Bercovich, Talor Abramovich, Daniel Afrimi et al.2026 · 0 citationsarXiv
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2606.15007v1 · NVIDIA: Aaron Blakeman, Aaron Thomas, Aastha Jhunjhunwala et al.2026 · 0 citationsarXiv
X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation2605.21699v1 · Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge, Mingyu Yang et al.2026 · 0 citationsarXiv
Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control2605.07182v1 · Ali Taghibakhshi, Ruisi Cai, Saurav Muralidharan et al.2026 · 0 citationsarXiv
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2604.12374v1 · NVIDIA: Aakshita Chandiramani, Aaron Blakeman, Abdullahi Olaoye et al.2026 · 0 citationsarXiv
Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery2601.20088v3 · Meng Xin, Sweta Priyadarshi, Jingyu Xin et al.2026 · 0 citationsarXiv
NVIDIA Nemotron 3: Efficient and Open Intelligence2512.20856v1 · NVIDIA: Aaron Blakeman, Aaron Grattafiori, Aarti Basant et al.2025 · 1 citationarXiv
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2512.20848v1 · NVIDIA: Aaron Blakeman, Aaron Grattafiori, Aarti Basant et al.2025 · 0 citationsarXiv
Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs2511.16664v1 · Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan et al.2025 · 0 citationsarXiv
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model2508.14444v4 · NVIDIA: Aarti Basant, Abhijit Khairnar, Abhijit Paithankar et al.2025 · 0 citationsarXiv
Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning2504.11409v2 · Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan et al.2025 · 0 citationsarXiv
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models2504.03624v4 · NVIDIA: Aaron Blakeman, Aarti Basant, Abhinav Khattar et al.2025 · 0 citationsarXiv
LLM Pruning and Distillation in Practice: The Minitron Approach2408.11796v4 · Sharath Turuvekere Sreenivas, Saurav Muralidharan, Raviraj Joshi et al.2024 · 3 citationsarXiv
Compact Language Models via Pruning and Knowledge Distillation2407.14679v2 · Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi et al.2024 · 30 citationsarXiv
GANBERT: Generative Adversarial Networks with Bidirectional Encoder Representations from Transformers for MRI to PET synthesis2008.04393v1 · Hoo-Chang Shin, Alvin Ihsani, Swetha Mandava et al.2020 · 13 citationsarXiv
GANDALF: Generative Adversarial Networks with Discriminator-Adaptive Loss Fine-tuning for Alzheimer's Disease Diagnosis from MRI2008.04396v1 · Hoo-Chang Shin, Alvin Ihsani, Ziyue Xu et al.2020 · 29 citationsarXiv
Career total: 20 works. 19 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.