Bryan Catanzaro
Source-listed: Vice President · NVIDIA
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismSaved credit: Contributor · 2019Explore people connected to this work →
- Megatron-LMSaved credit: Contributor · 2019Explore people connected to this work →
- Compact Language Models via Pruning and Knowledge DistillationSaved credit: Contributor · 2024Explore people connected to this work →
- Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of EncodersSaved credit: Contributor · 2025Explore people connected to this work →
- RLP: Reinforcement as a Pretraining ObjectiveSaved credit: Contributor · 2025Explore people connected to this work →