"au:"Lawrence McAfee"" — arXiv2 SearchShowing 1–9 of 9 results
/ Date/ Name
Apr 4, 2025Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer ModelsApr 13, 2023Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive StudyOct 11, 2023InstructRetro: Instruction Tuning post Retrieval-Augmented PretrainingJun 27, 2012Utilizing Static Analysis and Code Generation to Accelerate Neural NetworksOct 4, 2023Retrieval meets Long Context Large Language ModelsMay 10, 2022Reducing Activation Recomputation in Large Transformer ModelsAug 20, 2025NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning ModelDec 24, 2025NVIDIA Nemotron 3: Efficient and Open IntelligenceDec 23, 2025Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning