Model Detail

Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models

arXiv:2512.13607v2 Announce Type: replace-cross Abstract: Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response lengths and verification latency. Such variability complicates the

The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator

Nemotron-Personas-India: Synthesized Data for Sovereign AI

Nemotron-Personas-Japan: ソブリン AI のための合成データセット