Gerald Shen
NVIDIA engineer/researcher on NeMo-Aligner and Nemotron post-training infrastructure.
- Role
- engineer
- Currently at
- NVIDIA
- Unknown
- GitHub
- github.com/gshennvm
- Scholar
- scholar.google.com/scholar
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Llama-Nemotron: Efficient Reasoning Models
arXiv 2025
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arXiv 2025
HelpSteer2: Open-source Dataset for Training Top-Performing Reward Models
NeurIPS
Nemotron-4 340B Technical Report
arXiv 2024
Affiliations
Frequent co-authors
10from 4 papers
Jiaqi Zeng
researcher
Jimmy Zhang
researcher
Oleksii Kuchaiev
researcher
Olivier Delalleau
researcher
Aleksander Ficek
Ameya Sunil Mahabaleshwarkar
Boris Ginsburg
Bryan Catanzaro
researcher
Dan Su
Deepak Narayanan