Abstract: Techniques for initiating download of content are provided, including receiving, by one or more processors of the mobile computing device, an indication of a selection, made by a user of the mobile computing device, associated with third-party content provided by a proximate media player device; identifying, by the one or more processors of the mobile computing device, an indication of downloadable content associated with the third-party content displayed by the media player device; and downloading, by the one or more processors of the mobile computing device, in response to receiving the indication that the user selected the icon and without further input from the user, the downloadable content to a memory of the mobile computing device.

Abstract: A computer-implemented method for upmixing audiovisual data can include obtaining audiovisual data including input audio data and video data accompanying the input audio data. Each frame of the video data can depict only a portion of a larger scene. The input audio data can have a first number of audio channels. The computer-implemented method can include providing the audiovisual data as input to a machine-learned audiovisual upmixing model. The audiovisual upmixing model can include a sequence-to-sequence model configured to model a respective location of one or more audio sources within the larger scene over multiple frames of the video data. The computer-implemented method can include receiving upmixed audio data from the audiovisual upmixing model. The upmixed audio data can have a second number of audio channels. The second number of audio channels can be greater than the first number of audio channels.

Abstract: A method for active learning includes obtaining a set of unlabeled training samples and for each unlabeled training sample, perturbing the unlabeled training sample to generate an augmented training sample. The method includes generating, using a machine learning model, a predicted label for both samples and determining an inconsistency value for the unlabeled training sample that represents variance between the predicted labels for the unlabeled and augmented training samples. The method includes sorting the unlabeled training samples based on the inconsistency values and obtaining, for a threshold number of samples selected from the sorted unlabeled training samples, a ground truth label. The method includes selecting a current set of labeled training samples including each selected unlabeled training samples paired with the corresponding ground truth label. The method includes training, using the current set and a proper subset of unlabeled training samples, the machine learning model.

Abstract: A method including determining an eye-gaze characteristic of a user of a wearable device, determining a head movement of the user, determining a gesture based on the eye-gaze characteristic, the head movement, and a correlation between the eye-gaze characteristic and the head movement, selecting a user interface (UI) element of a head-locked UI operating on the wearable device based on the gesture, and triggering a UI operation based on the selected UI element.

Abstract: Systems and methods for providing visual indications of generative model responses can include obtaining a user input and processing the user input with a generative model to generate a model-generated-response. The systems and methods can process the model-generated response and an image of an environment to generate an augmented image. The augmented image can include visual indicators of the model-generated response, which can include annotating the image based on detected features within the image. Generation of the augmented image can include object detection and annotation based on the content of the model-generated response.

Abstract: Disclosed is the technology for computer-based “Daily Brief” service, which includes methods and corresponding systems for proactively providing push notifications for users of chat information systems. The push notifications are dynamically generated and presented to the user based on identification of one or more triggering events, which may include predetermined time/date, current geographical location, activity of peers and friends in social media associated with the user, scheduled events, appointments, meetings, emails, instant messages, and many more. The described technology improves the interaction interface between the user and chat information system.

Abstract: Implementations relate to an automated assistant that can proactively detect and respond to a request for credentials. Characteristics of an entity requesting the credentials can be preemptively determined by the automated assistant using data that may be provided by the user or other previous visitors to a location. For example, the automated assistant can determine that the entity may expressly request certain information from a user when the user arrives at the location. Based on this determination, the automated assistant can operate to initialize an interface of a computing device of the user, when the user is determined to be at or near the location. For example, an audio interface of the computing device can be initialized to capture an audible request from a person who views credentials before granting access to a feature of the location.

Abstract: Implementations are described herein for identifying related source code edits to perform, or to aid in the performance of, various programming tasks. In various implementations, a first edit made to a first source code snippet in a source code editor may be detected. Based on the first edit, a second source code edit to be made to a second source code snippet may be identified. The identifying may include: traversing one or more graphs to determine one or more edge sequences between nodes corresponding to the first and second source code snippets, comparing the one or more edge sequences to a plurality of reference edge sequences between nodes corresponding to historical co-occurrences of the first and second code edits, and identifying the second edit based on the comparing. The source code editor may provide output that includes a recommendation to implement the second edit.

Abstract: Implementations set forth herein relate to generating a pre-call analysis for one or more users that are receiving and/or initializing a call with one or more other users, and/or prioritizing pre-call content according to whether security-related value was gleaned from provisioning certain pre-call content. One or more machine learning models can be employed for determining the pre-call content to be cached and/or presented prior to a user accepting a call from another user. Feedback provided before, during, and/or after the call can be used as a basis from which to prioritize certain content and/or sources of content when generating pre-call content for a subsequent call. Other information, such as contextual data (e.g., calendar entries, available peripheral devices, location, etc.) corresponding to the previous call and/or the subsequent call, can also be used as a basis from which to provide a pre-call analysis.

Abstract: Techniques are described herein for segmenting source code into syntactically coherent sequences of tokens that satisfy constraints inherent in sequence-to-sequence networks. In various implementations, source code may be processed to generate one or more graphs representing the source code. One or more of the graphs may then be traversed to identify one or more sequences of tokens within the source code that satisfy an input constraint of a sequence-to-sequence network. The source code may be segmented into the identified one or more sequences of tokens. The one or more sequences of tokens may then be processed using the sequence-to-sequence network.

Abstract: A computing system can include one or more non-transitory computer-readable media that collectively store a neural network including one or more layers with relaxed spatial invariance. Each of the one or more layers can be configured to receive a respective layer input. Each of the one or more layers can be configured to convolve a plurality of different kernels against the respective layer input to generate a plurality of intermediate outputs, each of the plurality of intermediate outputs having a plurality of portions. Each of the one or more layers can be configured to apply, for each of the plurality of intermediate outputs, a respective plurality of weights respectively associated with the plurality of portions to generate a respective weighted output. Each of the one or more layers can be configured to generate a respective layer output based on the weighted outputs.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating subqueries from a query. In one aspect, a method includes obtaining a query, generating a set of two subqueries from the query, where the set includes a first subquery and a second subquery, determining a quality score for the set of two subqueries, determining whether the quality score for the set of two subqueries satisfies a quality threshold, and in response to determining that the quality score for the set of two subqueries satisfies the quality threshold, providing a first response to the first subquery that is responsive to a first operation that receives the first subquery as input and providing a second response to the second subquery that is responsive to a second operation that receives the second subquery as input.

Abstract: A computer-implemented method for compressing computer-readable data having improved efficiency can include obtaining, by a computing system including one or more computing devices, input data associated with the computing system; and encoding, by the computing system, the input data and added noise from a noisy channel to produce encoded data based at least in part on an encoder model, wherein encoding the input data and added noise includes additively combining the added noise and the input data to obtain noisy input data and rounding the noisy input data by a soft rounding function, the soft rounding function having a sharpness, to produce the encoded data, wherein the machine-learned encoder model is trained on training data, wherein the training data is encoded with the added noise from the noisy channel.

Abstract: Implementations set forth herein relate to interactions, between vehicle computing devices and mobile computing devices, that reduce duplicative processes from occurring at either device. Reduction of such processes can be performed, in some instances, via communications between a vehicle computing device and a mobile computing device in order to determine, for example, how to uniquely render content at an interface of each respective computing device while the user is driving the vehicle. These communications can occur before a user has entered a vehicle, while the user is in the vehicle, and/or after a user has left the vehicle. For instance, just before a user enters a vehicle, a vehicle computing device can be primed for certain automated assistant interactions between the user and their mobile computing device. Alternatively, or additionally, the user can authorize the vehicle computing device to perform certain processes immediately after leaving the vehicle.

Abstract: Implementations perform, independent of any explicit assistant invocation input(s), automatic speech recognition (ASR) on audio data, that is detected via microphone(s) of an assistant device, to generate ASR text that predicts a spoken utterance that is captured in the audio data. The ASR text is processed and candidate automated assistant action(s) that correspond to the command, if any, are generated. For each of any candidate automated assistant action(s), it is determined whether to (a) cause automatic performance of the automated assistant action responsive to the spoken utterance or, instead, (b) suppress any automatic performance of the automated assistant action responsive to the spoken utterance. Such determination can be made based on processing both (i) action feature(s) for the candidate automated assistant action; and (ii) environment feature(s) that each reflects a corresponding current value for a corresponding dynamic state of an environment of the assistant device.