Abstract: A method for handling timing conflicts associated with a random channel access procedure is implemented in a user device, and includes determining (314) that a first time span for the user device to transmit at least a data portion of a random-access procedure message to a base station overlaps a second time span for the user device to transmit another signal to the base station. The method also includes determining (320), based at least on a type of the other signal, a transmission precedence indicative of whether to modify transmission timing for the random-access procedure message or to instead modify transmission timing for the other signal, and, based on the determined transmission precedence, either transmitting (340) at least the data portion of the random-access procedure message to the base station during the first time span or transmitting (340) the other signal to the base station during the second time span.

Abstract: An interstitial creation interface is provided for display on a user device, the interstitial creation interface comprising a selectable interstitial indicator to add an interstitial to a playlist comprising a plurality of media items, wherein the selectable interstitial indicator is to be positioned between a first media item and a second media item of the plurality of media items. Responsive to a user selection of the selectable interstitial indicator, presentation of a plurality of user interface (UI) elements is caused to allow a user of the user device to specify interstitial configuration parameters for the interstitial being added to the playlist. User input is received for at least a subset of the plurality of UI elements to specify the interstitial configuration parameters for the interstitial.

Abstract: To provide navigation directions for a scenic route, a machine learning model is trained using (i) characteristics of road segments that have been assigned a scenic metric and (ii) the scenic metrics for the road segments. In response to a request for navigation directions, a set of candidate routes for navigating from the starting location to the destination location is identified. Then for each road segment within each candidate route, characteristics of the road segment are applied to the machine learning model to generate the scenic metric for the road segment. A route is then selected from the set of candidate routes based at least in part on the scenic metrics of the road segments within the route. A set of navigation directions is provided for presentation on a client device for navigating from the starting location to the destination location via the selected route.

Abstract: Systems and methods of the present disclosure can include a computer-implemented method for efficient machine-learned model training. The method can include obtaining a plurality of training samples for a machine-learned model. The method can include, for one or more first training iterations, training, based at least in part on a first regularization magnitude configured to control a relative effect of one or more regularization techniques, the machine-learned model using one or more respective first training samples of the plurality of training samples. The method can include, for one or more second training iterations, training, based at least in part on a second regularization magnitude greater than the first regularization magnitude, the machine-learned model using one or more respective second training samples of the plurality of training samples.

Abstract: Personalized network searching, in which a search query is received from a user, and a request is received to personalize a search result. Responsive to the search query and the request to personalize the search result, a personalized search result is generated by searching a personalized search object. Responsive to the search query, a general search result is generated by searching the general search object. The personalized search result and the general search result are provided to a client device, an advertisement is selected based at least in part upon the personalized search object, and the advertisement, the personalized search result, and the general search result are displayed.

Abstract: Implementations set forth herein relate to an automated assistant that can control graphical user interface (GUI) elements via voice input using natural language understanding of GUI content in order to resolve ambiguity and allow for condensed GUI voice input requests. When a user is accessing an application that is rendering various GUI elements at a display interface, the automated assistant can operate to process actionable data corresponding to the GUI elements. The actionable data can be processed in order to determine a correspondence between GUI voice input requests to the automated assistant and at least one of the GUI elements rendered at the display interface. When a particular spoken utterance from the user is determined to correspond to multiple GUI elements, an indication of ambiguity can be rendered at the display interface in order to encourage the user to provide a more specific spoken utterance.

Abstract: Implementations set forth herein relate to effectuating device arbitration in a multi-device environment using data available from a wearable computing device, such as computerized glasses. The computerized glasses can include a camera, which can be used to provide image data for resolving issues related to device arbitration. In some implementations, a direction that a user is directing their computerized glasses, and/or directing their gaze (as detected by the computerized glasses with prior permission from the user), can be used to prioritize a particular device in a multi-device environment. A detected orientation of the computerized glasses can also be used to determine how to simultaneously allocate content between a graphical display of the computerized glasses and another graphical display of another client device. When content is allocated to the computerized glasses, content-specific gestures can be enabled and actionable at the computerized glasses.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for facilitating input by a user into a form. In one aspect, a method include actions of obtaining a web resource that includes a form, determining a particular field of the form has been selected, determining an intent that corresponds to the form from a first semantic tag in the web resource, determining a parameter of the intent that corresponds to the particular field of the form from a second semantic tag in the web resource, determining a value to suggest for the particular field based at least on the intent and the parameter of the intent, and providing the value for output as a suggestion of input for the particular field.

Abstract: Systems and methods are provided that train a machine-learned language encoding model through the use of a contrastive learning task. In particular, the present disclosure describes a contrastive learning task where the encoder learns to distinguish input tokens from plausible alternatives. In some implementations, on each training example the proposed method masks out some subset (e.g., 15%) of the original input tokens, replaces the masked tokens with samples from a “generator” (e.g., which may be a small masked language model), and then trains the encoder to predict whether each token comes from the original data or is a replacement produced by the generator.

Abstract: Display systems, such as near eye display systems or wearable heads up displays, may include a laser projection system having an optical engine and an optical scanner. Light output by the optical engine may be directed into the optical scanner as two angularly separated laser light beams. The angularly separated laser light beams may overlap at an entrance pupil plane along a first dimension at a first scan mirror of the optical scanner, or at a location between the first scan mirror and an optical relay of the optical scanner. The angularly separated laser light beams may overlap at an exit pupil plane along the first dimension at a second scan mirror of the optical scanner or at an incoupler of the laser projection system.

Abstract: The present disclosure is directed to systems and methods of configuring a resource for network traffic analysis. An agent executed by a computing device receives an indication to record a browsing session. The agent records network activity data of the browsing session. The agent generates a data file with the recording. The agent transmits the data file and a request to generate a report to an analytics server. The analytics server receives the request and extracts the network activity data from the data file. The analytics server applies an event processing protocol to the network activity data. The analytics server generates a report and transmits the report to the client device for display.

Abstract: Systems and methods for providing referrer data to an application are provided. One method includes receiving a first set of data packets indicating a command to navigate from a first resource to a second resource. The first set of data packets identifies the first resource and secondary referrer data associated with the first resource or a first content item on the first resource. The method includes rendering the second resource and a second content item provided within the second resource. The method includes receiving a selection of the second content item. The method includes generating a second set of data packets including the secondary referrer data and primary referrer data associated with the second resource or the second content item. The method includes transmitting the second set of data packets to a server, receiving a deeplink generated by the server, and rendering a content interface using the deeplink.

Abstract: The present disclosure is directed to systems and methods that include a machine-learned label embedding model that generates feature-based label embeddings for labels in real-time, in furtherance, for example, of selection of labels relative to a particular entity. In particular, one example computing system includes both a machine-learned entity embedding model configured to receive and process entity feature data descriptive of an entity to generate an entity embedding for the entity and a machine-learned label embedding model configured to receive and process first label feature data associated with a first label to generate a first label embedding for the first label.

Abstract: A computer-implemented method for predicting speeds for a particular vehicle type includes receiving first tracking data indicative of individual speeds of first vehicles while traveling on road segments at various times, and second tracking data indicative of individual speeds of second vehicles while traveling on the same road segments at the same times. The second vehicles correspond to the particular vehicle type. The method also includes training a machine learning model to predict speeds for the particular vehicle type using a feature set based on the individual speeds indicated by the first tracking data and labels based on the individual speeds indicated by the second tracking data. The method further includes using the model to predict a speed of a vehicle (of the particular type) on a road segment, at least by processing a real-time speed estimate corresponding to other vehicles traveling on the same road segment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for contextually disambiguating queries are disclosed. In an aspect, a method includes receiving an image being presented on a display of a computing device and a transcription of an utterance spoken by a user of the computing device, identifying a particular sub-image that is included in the image, and based on performing image recognition on the particular sub-image, determining one or more first labels that indicate a context of the particular sub-image. The method also includes, based on performing text recognition on a portion of the image other than the particular sub-image, determining one or more second labels that indicate the context of the particular sub-image, based on the transcription, the first labels, and the second labels, generating a search query, and providing, for output, the search query.

Abstract: A system and method for updating and correcting facts that receives proposed values for facts from users and determines a correctness score which is used to automatically accept or reject the proposed values.

Abstract: Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for providing content. Publisher input is received regarding acceptable content item types and sizes for inclusion with other content in a publication. Publisher input is received regarding how often content items are to appear in the publication. Identification is received of a user device that will render the publication as an article. The other content is evaluated including formatting the article as a single scrolling page, including defining logical pages with boundaries determined by formatted content blocks and based on display capabilities of the user device. Based on the evaluating, content items are selected for presentation along with the other content when presenting the article on the user device, including dynamically determining a number, types and placement of content items based on the logical pages and properties of the user device.

Abstract: A computing system receives requests from client devices to process voice queries that have been detected in local environments of the client devices. The system identifies that a value that is based on a number of requests to process voice queries received by the system during a specified time interval satisfies one or more criteria. In response, the system triggers analysis of at least some of the requests received during the specified time interval to trigger analysis of at least some received requests to determine a set of requests that each identify a common voice query. The system can generate an electronic fingerprint that indicates a distinctive model of the common voice query. The fingerprint can then be used to detect an illegitimate voice query identified in a request from a client device at a later time.