Nvidia's Nemotron-Cascade 2 wins math and coding gold medals with 3B active parameters — and its post-training recipe is now open-source

Nvidia's Nemotron-Cascade 2 is a 30B MoE model that activates only 3B parameters at inference time, yet achieved gold ...
Frontiers

Teacher Learning and Scalable Continuing Professional Development in the Context of Global Emergencies: 5 Years on from the Global Uncertainties of the Covid-19 Pandemic

The global tragedies and profound public health and social uncertainties caused at the time of the Covid-19 pandemic placed a significant global spotlight ...