Abstract: Aspects of the present disclosure are directed to translating application calls for on-device machine learning execution. A translation layer supports on-device machine learning execution by translating JavaScript software application call data to achieve interoperability with on-device machine learning models. For example, JavaScript software applications interact with data, such as images, audio, video, and/or text, in a format or data type that is compatible with the application. On the other hand, machine learning models interact with data in a form conducive to mathematical operations, such as a data structure representation (e.g., tensor representation). Implementations translate data types and/or data files to provide compatible data to each of a native JavaScript software application and on-device machine learning models.

Abstract: In one embodiment, a method includes receiving code including multiple snippets programmed for manipulating objects in an extended reality environment; using a machine-learning model to learn to identify multiple coding patterns from the multiple snippets programmed for manipulating objects; extracting, based on the multiple coding patterns, object terms and relationships between the object terms used in the multiple snippets; generating an ontology for a natural language model based on the object terms and the relationships, wherein the ontology is configured to be used by the natural language model to parse speech into intents and slots.

Abstract: A content server delivers video segments to various on-site modules for display at the respective on-site modules according to respective schedules. The on-site modules may, for example, be located in coffee shops, convenience stores, sandwich grottos, and other establishments where customers are known to wait in line. The on-site modules also display call-in instructions, including a telephone number and a code. When a user places a call to a designated number and enters the code, an audio server determines the state of progression of the video, and begins synchronized audio playback over the caller's telephone.

Abstract: A content server delivers video segments to various on-site modules for display at the respective on-site modules according to respective schedules. The on-site modules may, for example, be located in coffee shops, convenience stores, sandwich grottos, and other establishments where customers are known to wait in line. The on-site modules also display call-in instructions, including a telephone number and a code. When a user places a call to a designated number and enters the code, an audio server determines the state of progression of the video, and begins synchronized audio playback over the caller's telephone.