Get the latest tech news
Apple aims for on-device user intent understanding with UI-JEPA models
At a few billion parameters, UI-JEPA models can understand user interactions without sending sensitive data to the cloud.
UI-JEPA draws inspiration from the Joint Embedding Predictive Architecture (JEPA), a self-supervised learning approach introduced by Meta AI Chief Scientist Yann LeCun in 2022. “This results in improved training and sample efficiency, by a factor of 1.5x to 6x as observed in V-JEPA, which is critical given the limited availability of high-quality and labeled UI videos.” This combination of a JEPA-based encoder and a lightweight LM enables UI-JEPA to achieve high performance with significantly fewer parameters and computational resources compared to state-of-the-art MLLMs.
Or read this on Venture Beat
