Watch ItFine-tuning
Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
NVIDIA Cosmos Predict 2.5 is a large-scale model designed for generating videos based on text and images, which can be fine-tuned using LoRA and DoRA methods. This approach allows for parameter-efficient training on a single GPU. However, it requires careful management of adapters for different domains, which can complicate deployment.
May 18, 2026
Read →EMO: Pretraining mixture of experts for emergent modularity
EMO is a mixture-of-experts model featuring 1 billion active parameters and 14 billion total parameters, trained on 1 trillion tokens. It allows users to utilize only 12.5% of its experts while maintaining near full-model performance. However, integration into existing workflows may be complex and costly.
May 11, 2026
Read →