Abstract: Methods and systems described herein for validating machine learning models in federated machine learning model environments. More specifically, the methods and systems relate to unloading training and validation techniques to client devices using newly collected data to improve accuracy of federated machine learning models.

Abstract: Methods and systems are described herein for protecting client data while training machine learning models. The system may transmit, to client devices, simple models to be trained on a respective client device to generate predictions based on a respective subset of respective client data of the respective client device. The system may receive the trained simple models from the client devices. The system may input, into an ensemble model including the simple models, an unlabeled synthetic dataset. This may cause the ensemble model to aggregate a set of predictions generated by each simple model to generate labels for the unlabeled synthetic dataset. The system may then input, into a new model, the unlabeled synthetic dataset and the labels to train the new model to predict the labels for the unlabeled synthetic dataset.

Abstract: A system for treating a gas turbine component to effectuate a change in a surface of the gas turbine component is disclosed. The system includes a composite blast media configured to be propelled onto the surface of the gas turbine component using a media blasting device. The composite blast media includes a carrier material and abrasive media embedded in the carrier material. The carrier material entraps at least a part of a substance released from the surface upon contact with the composite blast media.

Abstract: The input of a user is monitored and a location of the user and a language of the user are detected. The input is converted to a text string in the detected user language and the converted text string is parsed into parsed tokens. A command line and correlated parameters indicated by the input are recognized based on the parsed tokens. The recognized command line with the assigned parameters is executed.

Abstract: Methods and systems for generating federated learning models. In some aspects, the system receives, from each client device, user data profiles that are anonymized with respect to users associated with user data stored locally at a client device. The system processes the user data profiles to generate a plurality of clusters. For each cluster, the system transmits, to one or more client devices corresponding to a cluster, a first instruction to train a machine learning model on user data corresponding to user data profiles included in the cluster and a second instruction to validate the machine learning model with respect to user data corresponding to one or more clusters of the plurality of clusters other than the cluster to generate a prediction accuracy metric. The system determines, from the plurality of clusters, a first cluster based on associated prediction accuracy metrics.

Abstract: A facility for generating 3D models for mixed reality applications using generative artificial intelligence displays a mixed reality (MR) development environment. The facility obtains input describing a subject of the 3D model to be generated. The input may be a textual description of the subject or an image depicting the subject. The facility determines a target MR device with which the 3D model is to be displayed. The facility establishes a prompt based on the model description and the target device, and submits the prompt to a generative artificial intelligence (AI) model. The facility receives a 3D model from the generative AI model and displays the 3D model in the mixed reality development environment. Based on the mixed reality development environment, the facility creates a mixed reality application executable by the target MR device to display the 3D model.

Abstract: Methods and systems are described for novel uses and/or improvements to federated learning. As one example, methods and systems are described for improving the applicability of federated learning across various applications and increasing the efficiency of training a global model through federated learning. As another example, methods and systems are described for ensuring comprehensive training data is available to models assigned by the federated learning server. Additionally, methods and systems are described for improving the rate of training a global model through federated learning.

Abstract: A facility for providing an XR device-based tool for cross-platform content creation and display is disclosed. The facility causes a definition of a mixed reality (MR) procedure to be presented by an editing MR device in a virtual application window. Input is received via the editing MR device. The facility interprets the received input as one or more editing actions performed with respect to the MR procedure definition and alters the MR procedure definition accordingly. The facility creates a device-independent representation of the MR procedure based on the altered MR procedure definition.

Abstract: The facility provides an environment for creating a mixed reality (MR) application. Input specifying a property of a networked device is to be accessible in the mixed reality application is received. Properties of one or more networked devices are identified. A property selection interface is provided in the environment for creating the mixed reality application. The facility receives, via the property selection interface, selection of a networked device of the one or more networked devices and a property of the networked device. The facility configures the MR application to provide, to a device executing the MR application, access to the selected property of the selected networked device. The MR device can execute the MR application to access the selected property of the selected networked device.

Abstract: The systems and methods use a divergent artificial intelligence architecture. To summarize contextually relevant information on user-selected concepts despite the lack of adequate training data on each user, the system may use an architecture in which a first model is trained to map a plurality of user interactions to inputted concept identifiers to determine user relationship matrices whereas a second model is trained to generate contextually relevant summaries on inputted concepts and inputted user relationship matrices. For example, by using this divergent structure, the system does not need to be specifically trained to generate contextually relevant summaries based on each individual user's relationship to a given concept.

Abstract: A portion of a source mixed reality (MR) experience is retrieved. Then, the portion of the source MR experience is used to generate a serialized representation including a hierarchy of tagged elements. The hierarchy of tagged elements includes a plurality of MR step elements collectively defining a procedure to be performed by a viewer of an MR experience. Each MR step element has child elements that include an MR step number indicating a position of the MR step in the MR procedure and an MR step ID element indicating an identity of the MR step. The serialized representation is deserialized to generate a portion of a target MR experience to be edited in an MR development tool. The portion of the target MR experience is usable to cause each MR step in the plurality of MR steps to be graphically represented in the MR development tool.

Abstract: Methods and systems are described herein for protecting client data while training machine learning models. The system may transmit, to client devices, simple models to be trained on a respective client device to generate predictions based on a respective subset of respective client data of the respective client device. The system may receive the trained simple models from the client devices. The system may input, into an ensemble model including the simple models, an unlabeled synthetic dataset. This may cause the ensemble model to aggregate a set of predictions generated by each simple model to generate labels for the unlabeled synthetic dataset. The system may then input, into a new model, the unlabeled synthetic dataset and the labels to train the new model to predict the labels for the unlabeled synthetic dataset.

Abstract: Described herein are systems, methods, and programming for facilitating user-specific data transfers to provide task-related context to a user. In response to receiving a request to execute a computing task, one or more artificial intelligence models may generate a representation of the request encoding information about the request. The artificial intelligence models may identify another representation of another request that is similar to the generated representation. The similarity may indicate that another user previously submitted a request to execute a computing task that is similar to the requested computing task. This other representation may be selected and provided to a requesting user's device with a data transfer program configured to cause a decoder implemented by the requested user's device to extract the information encoded by the provided representation. The requesting user can use the extracted information to execute the computing task.

Abstract: A processor of a card may determine a predetermined voltage associated with the card. The processor may receive an indication of a voltage received from a terminal, wherein the card is powered by the voltage received from the terminal. The processor may determine that the voltage received from the terminal is not equal to the predetermined voltage associated with the card. The processor may reject, based on the determination that the voltage received from the terminal is not equal to the predetermined voltage associated with the card, a request from the terminal to provide payment information associated with the card.

Abstract: Systems and methods are disclosed herein for generating updated descriptions of items based on analyzing candidate embeddings of semantic representations of item descriptions. The system may obtain a text file describing an item. The system may provide the text file to a generative language model to generate semantic representations of the text file. The system may generate, based on the text file, candidate embeddings in an embedding space. The system may obtain embeddings associated with existing items. The system may determine subsets of the embeddings within a threshold distance. The system may compare the subsets. The system may determine attributes associated with a candidate embedding based on the comparison. The system may generate an updated text file based on the attributes.

Abstract: Systems and methods for triggering token alerts. In some aspects, the system, after determining that the probability that an authentication request from an authentication token is associated with a malicious activity is above a threshold, determines whether a user device associated with the authentication token is within a threshold distance of the authentication token. In response to determining that the authentication token is not within the threshold distance of the user device, the system declines the authentication request and transmits an alert request to the authentication token to emit an audio signal from a speaker included in the authentication token.

Abstract: Methods and systems are described herein for protecting client data while training machine learning models. The system may transmit, to client devices, simple models to be trained on a respective client device to generate predictions based on a respective subset of respective client data of the respective client device. The system may receive the trained simple models from the client devices. The system may input, into an ensemble model including the simple models, an unlabeled synthetic dataset. This may cause the ensemble model to aggregate a set of predictions generated by each simple model to generate labels for the unlabeled synthetic dataset. The system may then input, into a new model, the unlabeled synthetic dataset and the labels to train the new model to predict the labels for the unlabeled synthetic dataset.