Nvidia's Nemotron-Cascade 2 is a 30B MoE model that activates only 3B parameters at inference time, yet achieved gold medal-level performance at the 2025 IMO, IOI, and ICPC World Finals. Nvidia has ...
Researchers at the University of Science and Technology of China have developed a new reinforcement learning (RL) framework that helps train large language models (LLMs) for complex agentic tasks ...