【#Tech24H】A research team led by Turing Award winner Yann LeCun recently released LeWorldModel (LeWM), a new lightweight world model. It fundamentally addresses issues common in traditional JEPA models, such as training instability, collapse, excessive hyperparameters, and high computational costs. It is the first world model capable of stable end-to-end training directly from raw pixels. The model consists of just two core components, two loss terms, and 15 million parameters, requiring only a few hours of training on a single GPU, with only one effective tunable hyperparameter. In addition, LeWM achieves a qualitative leap in planning speed, reaching up to 48 times that of traditional large model methods, with a single planning session taking less than one second.