Abstract: A method of emulating a user's interactions with an application is disclosed. The method includes: training a large action model (LAM) to interact with the application using demonstrations; receiving a user intention; generating, by the LAM, executable code in response to the user intention; and executing the executable code to initialize an agent host configured to interact with the application.

Abstract: A system for processing a data stream is disclosed. The system includes a client and a server, the client in communication with the server, wherein the client is configured to divide the data stream into a plurality of data chunks and transmit the data chunks one by one to the server; wherein the server is configured to start processing the data chunks transmitted from the client before the client finishes transmitting all of the plurality of data chunks; wherein the server is further configured to transmit processed data chunks to the client in a streaming fashion; and wherein the client is further configured to play back the processed data chunks one by one immediately upon receiving the processed data chunks from the server.

Abstract: A computer-implemented method of interacting with a computer application through a user interface is disclosed. The method includes determining if the computer application is in a state ready to be observed, reasoned, and interacted with; identifying an element in the computer application to interact with; and determining an action to use on the identified element and information required to execute the action; wherein identifying the element in the computer application to interact with includes extracting and storing one of more features of a reference element from a reference document object model (DOM); and given a target DOM, finding the element in the target DOM that corresponding to the reference element.

Abstract: An artificial intelligence enabled system is disclosed. The system includes a core component for enabling AI-powered interactions between the system and its users and one or more agents that understand user intent and automatically interact with products and services on the web and/or in the physical world through imitation of a human user.

Abstract: A method of training a system to interact with an application is disclosed. The system includes an interface model configured to translate one or more requests into a sequence of user interface (UI) actions on the application; the interface model comprising: a static model configured to understand UI components of an application; and a dynamic model configured to understand interactions among the UI components and operations that occur when a UI action is completed. The method includes: recording a demonstration of interacting with the application; converting, by the static model, the demonstration into an intermediate representation (IR); and examining the IR, by the dynamic model, to determine an entity, transition, and semantic of an UI that is part of the demonstration.

Abstract: An artificial intelligence enabled system is disclosed. The system includes a core component for enabling AI-powered interactions between the system and its users and one or more agents that understand user intent and automatically interact with products and services on the web and/or in the physical world through imitation of a human user.

Abstract: An artificial intelligence enabled system is disclosed. The system includes a core component for enabling AI-powered interactions between the system and its users and one or more agents that understand user intent and automatically interact with products and services on the web and/or in the physical world through imitation of a human user.

Abstract: Multiple-patterning techniques described herein enable forming fin structures of a semiconductor device in a manner that enables decreased fin-to-fin spacing of the fin structures while providing precise control over etching depth of the fin structures. In some implementations, an etch operation is performed to form a pattern in one or more mask layers that is used to etch a substrate to form the fin structures. The etch operation includes an advanced pulsing technique, in which a high-frequency radio frequency (RF) source and a low-frequency RF source are pulsed. Pulsing the high-frequency RF source and the low-frequency RF source in the etch operation reduces consumption of a thickness of the one or more mask layers which increases the aspect ratio of the pattern. This enables deeper etching of the substrate when forming the fin structures, which reduces the likelihood of under etching.

Abstract: Systems and methods for determining an order accepting mode for a target service provider are provided. A method includes receiving a request for determining an order accepting mode for the target service provider. The method also includes obtaining an order accepting evaluation parameter with respect to the target service provider in response to the request. The method also includes determining an order accepting mode for the target service providers based on the order accepting evaluation parameter. The order accepting mode includes at least one of an order designating mode, an order striving mode, or an order quick-accepting mode.

Abstract: Systems and methods for determining an order accepting mode for a target service provider are provided. A method includes receiving a request for determining an order accepting mode for the target service provider. The method also includes obtaining an order accepting evaluation parameter with respect to the target service provider in response to the request. The method also includes determining an order accepting mode for the target service providers based on the order accepting evaluation parameter. The order accepting mode includes at least one of an order designating mode, an order striving mode, or an order quick-accepting mode.