Mostofa Patwary

Computer Science · Physical Sciences

15h-index2.2kcitations69works0.92yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(30), Natural Language Processing Techniques(28), Multimodal Machine Learning Applications(12), Speech Recognition and Synthesis(4), Graph Theory and Algorithms(4)

Publications62 total

Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs
arXiv (Cornell University)·2025Open Access
Pretraining Large Language Models with NVFP4
arXiv (Cornell University)·2025Open Access
RLP: Reinforcement as a Pretraining Objective
arXiv (Cornell University)·2025Open Access
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
arXiv (Cornell University)·2025Open Access
Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset
arXiv (Cornell University)·2025Open Access
FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
arXiv (Cornell University)·2025Open Access
Llama-Nemotron: Efficient Reasoning Models
arXiv (Cornell University)·2025· 1 citedOpen Access
Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
arXiv (Cornell University)·2025Open Access
Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
arXiv (Cornell University)·2025Open Access
Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
arXiv (Cornell University)·2025Open Access
Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset
2025· 1 citedOpen Access
Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining
arXiv (Cornell University)·2024Open Access
Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset
arXiv (Cornell University)·2024Open Access
MIND: Math Informed syNthetic Dialogues for Pretraining LLMs
arXiv (Cornell University)·2024Open Access
LLM Pruning and Distillation in Practice: The Minitron Approach
arXiv (Cornell University)·2024· 3 citedOpen Access
Compact Language Models via Pruning and Knowledge Distillation
arXiv (Cornell University)·2024· 10 citedOpen Access
Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models
arXiv (Cornell University)·2024· 4 citedOpen Access
Data, Data Everywhere: A Guide for Pretraining Dataset Construction
arXiv (Cornell University)·2024Open Access
Nemotron-4 340B Technical Report
arXiv (Cornell University)·2024· 6 citedOpen Access
Nemotron-4 15B Technical Report
arXiv (Cornell University)·2024Open Access
page 1 of 4Next →

Frequent Co-authors

Mohammad Shoeybi(34), Bryan Catanzaro(32), Shrimai Prabhumoye(14), Raul Puri(8), Patrick LeGresley(6), Jared Casper(6), Dan Su(6), Narayanan Sundaram(5), Prabhat(5), Anima Anandkumar(5), Deepak Narayanan(5), Joseph Jennings(5), Ameya Sunil Mahabaleshwarkar(5), Nadathur Satish(4), Brandon Norick(4), Pascale Fung(4), Ping Wei(4), Peng Xu(4), Fredrik Manne(4), Pradeep Dubey(4)