3 papers
cs.CL2026
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +571
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…
cs.CY2025
Building Effective Safety Guardrails in AI Education Tools
Hannah-Beth Clark, Laura Benton, Emma Searle +4
There has been rapid development in generative AI tools across the education sector, which in turn is leading to increased adoption by teachers. However, this raises concerns regar…
cs.CY2025
Auto-Evaluation: A Critical Measure in Driving Improvements in Quality and Safety of AI-Generated Lesson Resources
Hannah-Beth Clark, Margaux Dowland, Laura Benton +7
As a publicly funded body in the UK, Oak National Academy is in a unique position to innovate within this field as we have a comprehensive curriculum of approximately 13,000 open e…