Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for cross input modality learning in a mobile device are disclosed. In one aspect, a method includes activating a first modality user input mode in which user inputs by way of a first modality are recognized using a first modality recognizer; and receiving a user input by way of the first modality. The method includes, obtaining, as a result of the first modality recognizer recognizing the user input, a transcription that includes a particular term; and generating an input context data structure that references at least the particular term. The method further includes, transmitting, by the first modality recognizer, the input context data structure to a second modality recognizer for use in updating a second modality recognition model associated with the second modality recognizer.

Abstract: A replicated block storage service provides durable and high performance network-attached storage replicated in two or more zones of a single region, and remains available despite a single zone failure. A probe file is generated to determine a health state of a replicated disk. When a disk is degraded, a lease is created indicating which replica is trusted and providing visibility to backend jobs to facilitate reconciliation of data between the first replica and the second replica. Moreover, degraded file markers are generated for use by the backend jobs in quickly identifying the data to be copied.

Abstract: A method is implemented at an electronic device for displaying output from an application. The electronic device includes a display module and an application. The application sends to the display module a request to display output on the fixed orientation display. The display module determines whether the application is able to scale the output from the application to fit the fixed orientation display. In accordance with a determination that the application is able to scale the output, the electronic device causes the application to receive information concerning the fixed orientation display from the display module and scale the output for display on the fixed orientation display according to the information. In accordance with a determination that the application is not able to scale the output, the display module scales the output received from the application, thereby enabling the output of the application to be displayed on the fixed orientation display.

Abstract: Methods and systems for facilitating an equitable bandwidth distribution across downstream devices in asymmetrical switch topologies, and in particular asymmetrical PCIe switch topologies. The equitable distribution of bandwidth is achieved in asymmetrical topologies using virtual switch partitioning. An upstream switch that is connected to the root complex via an upstream port and that receives bandwidth B from the upstream port, is virtualized into two or more virtual switches. Each virtual switch equally shares the bandwidth. Each virtual switch is allocated to downstream devices that are connected to the upstream switch as well as to one or more downstream switches that are connected to the upstream switch. Each downstream switch may be connected to one or more additional downstream devices.

Abstract: The present disclosure describes aspects of an antenna-in-package (AiP) transceiver module and associated methods and systems. In aspects, an AiP transceiver module includes a substrate of dielectric material and first and second layers of conductive material disposed on respective surfaces of the substrate. The first layer of conductive material disposed on a first surface of the substrate includes an antenna element and antenna feed pad to which a contact of a transceiver integrated circuit die is coupled. The second surface of the substrate includes a dielectric interface area that is opposite to an area on the first surface of the substrate in which the antenna element is disposed and excludes the second layer of conductive material. The dielectric interface area of the substrate may effectively increase an amount of dielectric material below the antenna element, such that a volume of the dielectric material includes an air gap below the module.

Abstract: Systems and methods for adjusting light emitted from a display of a device are provided. The adjusting includes obtaining, from light of an environment detected by at least one sensor, a measured color of light of the environment, and obtaining, from light of the environment detected by at least one sensor, a measured brightness of light of the environment. In response to the obtaining the measured color and the measured brightness of light, a color of light emitted from the display is adjusted from an initial color prior to the adjusting to a target color that matches the measured color. Further, a brightness of light emitted from the display is adjusted from an initial brightness emitted by the display prior to the adjusting to a target brightness that matches the measured brightness of light.

Abstract: Provided is an in-ear device and associated computational support system that leverages machine learning to interpret sensor data descriptive of one or more in-ear phenomena during subvocalization by the user. An electronic device can receive sensor data generated by at least one sensor at least partially positioned within an ear of a user, wherein the sensor data was generated by the at least one sensor concurrently with the user subvocalizing a subvocalized utterance. The electronic device can then process the sensor data with a machine-learned subvocalization interpretation model to generate an interpretation of the subvocalized utterance as an output of the machine-learned subvocalization interpretation model.

Abstract: An actuator module includes a baseplate extending in a plane, a voice coil connected to the baseplate, and a magnet assembly. The actuator module also includes a rigid frame attached to the baseplate, the rigid frame comprising four stubs. The actuator module further includes a pair of springs suspending the magnet assembly relative to the frame and baseplate so that the voice coil extends into the air gap, the pair of springs including a first and second spring each shaped as a loop defining an aperture sized to accommodate motion of the magnet assembly along a direction of the coil axis, the first spring being attached to the frame at a first pair of the four stubs, the second spring being attached to the frame at a second pair of the four stubs, and both being attached to separate portions of the magnet assembly.

Abstract: The present disclosure describes one or more aspects of a space-saving, serviceable modular battery assembly that may be used as part of a user equipment. The space-saving, serviceable modular battery assembly includes a battery cell electrically coupled to a first module assembly that monitors a state of the battery cell, a first alignment bracket located at a first end of the battery cell, and a second alignment bracket located at a second end of the battery cell. The first module assembly overlaps a second module assembly that supports system-level functions of the user equipment.

Abstract: This disclosure relates to preserving the privacy of users and preventing access to information of other entities. In one aspect, a method includes receiving, from a client device, a content request including request signals specifying user group identifiers that each identify a user group that includes a user of the client device. One or more user group identifiers that satisfy a first k-anonymity process are identified. Selection parameter elements that each include data indicating a respective digital component and a selection parameter for the respective digital component are received from one or more first content platforms. At least a portion of the selection parameters and, for each selection parameter, data identifying the first content platform from which the selection parameter was received are transmitted to a second content platform. Data specifying a given first content platform selected based on the selection parameters is received from the second content platform.

Abstract: A method for pre-utilizing tables before refresh includes selecting a query for execution in a data analytics application and identifying a table specified by the query, for instance a materialized table. Another operation includes computing an encoding, such as a hash value, for at least one portion of the identified table. Another operation includes comparing the computed encoding to a pre-stored encoding for the at least one portion of the identified table. On the condition that the computed encoding is identical to the pre-stored encoding, the operations include utilizing the identified table in executing the query in lieu of re-materializing the identified table. Otherwise, on the condition that the computed encoding differs from the pre-stored encoding, the operations include re-materializing the identified table before returning the results of the query.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.

Abstract: The technology provides for allocating an available resource in a computing system by bidirectional communication between a hypervisor and a container scheduler in the computing system. The computing system for allocating resources includes one or more processors configured to receive a first scheduling request to initiate a first container on a first virtual machine having a set of resources. A first amount of resources is allocated from the set of resources to the first container on the first virtual machine in response to the first scheduling request. A hypervisor is notified in a host of the first amount of resources allocated to the first container. A second amount of resources from the set of resources is allocated to a second virtual machine in the host. A reduced amount of resources available in the set of resources is determined. A container scheduler is notified by the hypervisor for the reduced amount of resources of the set of resources available on the first virtual machine.

Abstract: Arrangements herein are directed to pin state detection systems and arrangements for using such systems. A pin detection system can include a pin. The pin can be in one of multiple states, such as a depressed state and an undepressed state. The system can include a transmit coil and a receive coil that encircles the pin. The system can also include a processing system that causes a transmit signal to be transmitted to the transmit coil. The processing system can analyze a signal received from the receive coil to determine a state of the pin.

Abstract: A system for simulating network configurations includes data processing hardware and memory hardware in communication with the data processing hardware. The memory hardware stores instructions that when executed on the data processing hardware cause the data processing hardware to perform operations. The operation includes receiving one or more parameter changes for a production network model of a network. The operations also include generating a simulation network model including the one or more parameter changes. Another operation includes analyzing the simulated network flow within the simulation network model. The operations also include generating a report including an impact of the parameter changes on the network. The operations may also include receiving a production network log including a recorded workflow for the production network model and simulating the production workflow of the production network log within the simulation network model to generate a simulated network log.

Abstract: This document describes systems and techniques directed at a multi-cut display-panel design enabling system integration into two or more end products. In aspects, a display panel includes a display panel body, having a pixel array and related electronics, as well as one or more border extensions disposed at least partially around a display border of the display panel body. The display panel further includes one or more cutting profiles to separate one or more borders extensions (or no border extensions) for integration in differently sized mounting structures of various electrical devices. Through these systems and techniques, a single display panel with a multi-cut design can be manufactured for integration within dissimilarly shaped electronic devices, saving costs associated with conventional manufacturing techniques, improving electronic device reliability, and antenna performance.

Abstract: Wearable devices using “legacy” sensors such as proximity sensors or infrared sensors suffer from false positives when, such as when they are placed in a hand, but not inserted on the user's body or on or into the user's ear. Embedding a PPG module or PPG sensor into the wearable device allows for the PPG module to act as a secondary check for the presence of a user wearing the wearable device. In some examples, the PPG module can be used as a sole sensor for the presence or absence of a human user. In other examples, a PPG module can be used to perform a secondary action after the “legacy” sensor performs a first action. For example, the first action can be connecting to a user device while the second action can be opening an application or playing music.

Abstract: Systems and methods for editing and generating digital ink. The present technology may provide systems and methods for training a handwriting model to generate digital ink that is stylistically and visually consistent with an original handwriting input, but which incorporates one or more changes to the text of the original handwriting input. In some examples, training may be performed using training examples that include an original handwriting sample and an original label representing the sequence of characters in the original handwriting sample. In such a case, the original handwriting sample may be processed to generate a style vector that is randomly masked, and the handwriting model may then be trained to generate a predicted handwriting sample that closely matches the original handwriting sample using the masked style vector and the original label as inputs.

Abstract: A method for turn detection in a speech-to-speech model includes receiving, as input to the speech-to-speech (S2S) model, a sequence of acoustic frames corresponding to an utterance. The method further includes, at each of a plurality of output steps, generating, by an audio encoder of the S2S model, a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames, and determining, by a turn detector of the S2S model, based on the higher order feature representation generated by the audio encoder at the corresponding output step, whether the utterance is at a breakpoint at the corresponding output step. When the turn detector determines that the utterance is at the breakpoint, the method includes synthesizing a sequence of output audio frames output by a speech decoder of the S2S model into a time-domain audio waveform of synthesized speech representing the utterance spoken by the user.

Abstract: A method for evaluating a verification model includes receiving a first and a second set of verification results where each verification result indicates whether a primary model or an alternative model verifies an identity of a user as a registered user. The method further includes identifying each verification result in the first and second sets that includes a performance metric. The method also includes determining a first score of the primary model based on a number of the verification results identified in the first set that includes the performance metric and determining a second score of the alternative model based on a number of the verification results identified in the second set that includes the performance metric. The method further includes determining whether a verification capability of the alternative model is better than a verification capability of the primary model based on the first score and the second score.