Abstract: An example medical device includes a device housing configured to be implantable within a patient, the device housing including an internal surface in contact with a voltaic cell of the battery, and a battery external to the device housing and comprising a battery housing configured to be hermetically sealed. The battery is configured to provide electrical power to an electrical component housed within the device housing, and the battery housing is configured to be attached to the device housing. The battery housing includes an internal surface in contact with a voltaic cell of the battery, and an external surface in contact with the biocompatible electrical insulator. an external surface in contact with the biocompatible electrical insulator.

Abstract: A system that includes a power transmitting antenna (124) with a coiled conductor defined by a first axis and a second axis perpendicular to the first axis, where a single plane comprises the first axis and the second axis. The system includes a support layer (140, 142) comprising: a substantially planar top surface and a substantially planar bottom surface opposite the substantially planar top surface arranged parallel to the plane. The support layer also comprises a material with a predetermined resiliency. The support layer is configured to support a mass of a user and maintain a predetermined spacing between the plane of the power transmitting antenna and the user during compression of the material from the mass of the user.

Abstract: A medical device includes wake circuitry and telemetry circuitry. The wake circuitry is configured to receive a first set of data from a device associated with the medical device, where the first set of data is received at a frequency band. The wake circuitry is configured to output a set of pulses based on the first set of data. The wake circuitry is configured to detect a data pattern using the set of pulses. The wake circuitry is configured to output an activation signal in response to a determination that the data pattern satisfies a data pattern requirement. The telemetry circuitry is configured to output a second set of data in response to receiving the activation signal. The second set of data is transmitted at the frequency band. The telemetry circuitry is configured to establish a communication session with the device using the second set of data.

Abstract: Systems and methods for machine learning context based confidence calibration are disclosed. In one embodiment, a processing logic may obtain an image frame; generate, with a first machine learning model, a confidence score, a bounding box, and an instance embedding corresponding to an object instance inferred from the image frame; and compute, with a second machine learning model, a calibrated confidence score for the object instance based on the instance embedding, the confidence score, and the bounding box.

Abstract: Systems and methods are described for improving portability of checkpoints of an application using central processing unit (CPU)-specific features. In an example, a system includes a source computing system and a destination computing system. The source computing system may be configured to: cause a first execution of an application that includes a function associated with a plurality of implementations; receive a request to resolve an implementation decision for the function; select, based on a set of source CPU-specific features, a source-specific implementation for the first execution of the function; patch, by rendering a resolved callsite table, a call site associated with the function with an address of the source-specific implementation; and send, to a destination computing system, a checkpoint of the application that includes the resolved callsite table.

Abstract: Embodiments provide systems, methods, and computer storage media for extracting semantic labels for field widgets of form fields in unfilled forms. In some embodiments, a processing device accesses a representation of a fillable widget of a form field of an unfilled form. The processing device generates an encoded input representing text and layout of a sequence of tokens in a neighborhood of the fillable widget. The processing device uses a machine learning model to extract a semantic label representing a field type of the fillable widget in view of the encoded input. The processing device causes execution of an action using the semantic label.

Abstract: An example system includes telemetry circuitry configured for communication between a medical device and an external device associated with the medical device and processing circuitry. The processing circuitry is configured to receive, with the telemetry circuitry, an advertisement from the medical device. The advertisement includes connection parameters for a potential communication session with the medical device and an indication that the medical device is connected by an established communication session between the medical device and a connected device. The processing circuitry is further configured to identify the connected device using the indication of the advertisement, initiate a communication session between the telemetry circuitry and the connected device, and output, with the telemetry circuitry and using the communication session between the telemetry circuitry and the connected device, a request for information from the medical device.

Abstract: Systems and methods are described for improving portability of virtual machine checkpoints without affecting system performance. In an example, a method includes determining, by a source computing system having a processor, via a virtual machine, and based on a runtime of an application on the virtual machine, one or more units of the application to compile as one or more non-portable units of the application; designating, as a non-entrant compiled code, the one or more non-portable units of the application, wherein the designation prevents execution of the one or more non-portable units; decompiling, by the source computing system, one or more stack frames associated with the one or more non-portable units of the application; sending, by the source computing system to a destination computing system, a checkpoint for the application; restoring, by the destination computing system via the virtual machine, from the checkpoint for the application, the runtime of the application.

Abstract: Systems and methods are described for improving portability of checkpoints of an application using central processing unit (CPU)-specific features. In an example, a system includes a source computing system and a destination computing system. The source computing system may be configured to: cause a first execution of an application that includes a function associated with a plurality of implementations; receive a request to resolve an implementation decision for the function; select, based on a set of source CPU-specific features, a source-specific implementation for the first execution of the function; patch, by rendering a resolved callsite table, a call site associated with the function with an address of the source-specific implementation; and send, to a destination computing system, a checkpoint of the application that includes the resolved callsite table.

Abstract: A method comprises determining instance bounds associated with each of one or more structural elements in a document using a machine learning model. The method further comprises determining an error in the instance bounds associated with a particular one of the one or more structural elements. The method further comprises correcting the error in the instance bounds associated with the particular structural element using document content associated with the particular structural element, thereby generating corrected instance bounds associated with the particular structural element. The method further comprises generating a structural map of the document based on the corrected instance bounds.

Abstract: Methods and systems are provided for facilitating identification of fillable regions and/or data associated therewith. In embodiments, a candidate fillable region indicating a region in a form that is a candidate for being fillable is obtained. Textual context indicating text from the form and spatial context indicating positions of the text within the form are also obtained. Fillable region data associated with the candidate fillable region is generated, via a machine learning model, using the candidate fillable region, the textual context, and the spatial context. Thereafter, a fillable form is generated using the fillable region data, the fillable form having one or more fillable regions for accepting input.

Abstract: Impedance matching in tunable circuits promotes consistent, high-efficiency wireless communication signal despite changing environmental conditions.

Abstract: In one example, a system includes telemetry circuitry configured for communication between a medical device and an external device associated with the medical device and processing circuitry. The processing circuitry is configured to determine an advertising interval for communication between the external device and the medical device based on sensor information from the external device. The processing circuitry is further configured to configure the medical device to advertise at the determined advertising interval.

Abstract: In one example, a system includes telemetry circuitry configured for communication between a medical device and an external device associated with the medical device and processing circuitry. The processing circuitry is configured to determine connection parameters for a connection between the medical device and the external device based on one or more of first information detected by the external device or second information detected by the medical device. The processing circuitry is further configured to output an advertisement for the connection between the medical device and the external device based on the connection parameters and establish the connection between the medical device and the external device according to advertisement.

Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.

Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.

Abstract: A method comprises determining instance bounds associated with each of one or more structural elements in a document using a machine learning model. The method further comprises determining an error in the instance bounds associated with a particular one of the one or more structural elements. The method further comprises correcting the error in the instance bounds associated with the particular structural element using document content associated with the particular structural element, thereby generating corrected instance bounds associated with the particular structural element. The method further comprises generating a structural map of the document based on the corrected instance bounds.

Abstract: Techniques are disclosed for identifying document structural elements and correcting errors in the classification and/or location of the identified structural elements. An example method includes determining location and classification for a structural element on a page of the document using a machine learning (ML) model; determining one or more errors in the location and/or classification for the structural element; and correcting each instance of the one or more errors using other content in the document (e.g., content spatially adjacent to the corresponding structural element on the page of the document). The method may further include storing the document and the location and classification (as corrected), and/or generating a structural map of the page of the document based on the location and classification (as corrected). The use of the document content to correct errors greatly enhances the agreement between the identified structural elements and the original document.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for creating visualizations to explain the outputs produced by models designed for object detection. To accomplish this, a graphics editing platform can obtain a reference output that identifies a region of pixels in a digital image that allegedly contains an object. Then, the graphics editing platform can compute the similarity between the reference output and a series of outputs generated by a model upon being applied to masked versions of the digital image. A visualization component can be produced based on the similarity.

Abstract: A method list is built for a currently executing application within a process virtual machine at a snapshot point, the method list comprising a set of methods capable of being executed by the currently executing application after the snapshot point, the snapshot point comprising an execution state of the currently executing application when a snapshot process is triggered. Profiling data of the currently executing application, collected prior to reaching the snapshot point, is committed, to a designated storage location. Using the profiling data and a just-in-time compiler of the process virtual machine, a method in the method list is compiled. Snapshot data comprising data of the execution state of the currently executing application at the snapshot point, including a result of the compiling, is stored.