Tag
NVIDIA Cosmos3, a 64B parameter image generation model, is released with INT4 quantization for local deployment on CUDA and MLX, with code and weights available and performance demonstrated on Apple Silicon.
The AI City Challenge at ECCV 2026 showcased winners developing robust visual AI systems, with top solutions in video forecasting using NVIDIA Cosmos world foundation models for tasks like scene understanding and prediction.
Engineers can use NVIDIA Cosmos with RoadRunner, MATLAB, and Simulink to generate photorealistic driving scenes for autonomous driving development, combining simulation for control and generative AI for visual diversity.
Introduces two projects related to robot world models: Awesome-WAM (OpenMOSS) includes papers such as World Action Models and DreamDojo; awesome-physical-ai curates a collection of papers on VLA models, world models, and embodied foundation models (including NVIDIA Cosmos Predict2.5).
A complete guide to fine-tuning NVIDIA's Cosmos Predict 2.5 world model using LoRA/DoRA for generating robot manipulation videos, covering dataset preparation, training, inference, and evaluation.