Abstract: Techniques are described herein for concurrent voice assistants. A method includes: providing first and second automated assistants with access to one or more microphones; receiving, from the first automated assistant, an indication that the first automated assistant has initiated a first session, and in response: continuing providing, to the first automated assistant, access to the one or more microphones; discontinuing providing, to the second automated assistant, access to the one or more microphones; and preventing the second automated assistant from accessing one or more portions of an output audio data stream; receiving, from the first automated assistant, an indication that the first session has ended, and in response: continuing providing, to the first automated assistant, access to the one or more microphones; resuming providing, to the second automated assistant, access to the one or more microphones; and resuming providing, to the second automated assistant, the output audio data stream.

Abstract: A computing platform configurable to allow users to graphically represent relationships between database records may be provided to a plurality of organizations. A request to generate a customizable visualization for graphically representing relationships between a root database record and child database records in a customizable format may be processed. Graphical representations of the root database record and the child database records may be caused to be displayed in accordance with the customizable format.

Abstract: System and method are disclosed for training a generative adversarial network pipeline that can produce realistic artificial depth images useful as training data for deep learning networks used for robotic tasks. A generator network receives a random noise vector and a computer aided design (CAD) generated depth image and generates an artificial depth image. A discriminator network receives either the artificial depth image or a real depth image in alternation, and outputs a predicted label indicating a discriminator decision as to whether the input is the real depth image or the artificial depth image. Training of the generator network is performed in tandem with the discriminator network as a generative adversarial network. A generator network cost function minimizes correctly predicted labels, and a discriminator cost function maximizes correctly predicted labels.

Abstract: Apparatuses and methods related to port arbitration of a memory system are described. A memory system can receive a first number of transactions and a second transaction from a first traffic stream and a third number of transactions and a fourth transaction from a second traffic stream. The memory system can process the first number of transactions at least partially concurrently with the third number of transactions. Responsive to a total quantity of transactions of the first number of transactions and the second transaction being at least a threshold quantity of transactions, the second transaction can be processed by the memory system and, subsequent to processing the second transaction, the fourth transaction can be processed by the memory system.

Abstract: Techniques for image processing including receiving input image data, wherein the input image data includes data associated with a clear color channel, receiving a color offset value associated with a color channel, wherein color values for the color channel are not provided in the input image data, based on the color offset value, generating intermediate estimated color values for the color channel, wherein generating the intermediate estimated color values includes: clipping color values that have a magnitude greater than the color offset value, and adjusting color values that have a magnitude less than the color offset value based on the color offset value, applying a color correction function to the intermediate estimated color values based on the color offset value to determine color corrected estimated color values, and outputting the color corrected estimated color values.

Abstract: A computer implemented method includes receiving input from a first collaborator user device to modify a cell in a collaborative spreadsheet being shared with other collaborators and viewable on other collaborator user devices, sending modifications via a real time channel to the other user devices for display of mirror modifications to the cell prior to commitment of the modifications, and providing an identifier of the first collaborative user device for display of a notice that the first user device is associated with the mirror modifications.

Abstract: In one aspect, an example method includes (i) identifying, by a playback device, a media device that provides media content to the playback device; (ii) providing, by the playback device, replacement media content for display; (iii) determining, by the playback device, that while the playback device is displaying the replacement media content a remote control transmitted an instruction to the identified media device; (iv) determining, by the playback device, a playback-modification action corresponding to the instruction and the identified media device; and (v) modifying, by the playback device, playback of the replacement media content in accordance with the playback-modification action.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, a plurality of electronic messages addressed to a user, (ii) analyzing, by a large language model executed by the processor, the plurality of electronic messages to identify potential actions, (iii) suggesting, by the processor, to the user, a potential action identified by the large language model, (iv) receiving, by the processor, user input related to the potential action, and (v) performing, by the processor, on behalf of the user, a subsequent action conforming to the user input.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) accessing, by a processor, a plurality of messages for a user, (ii) analyzing, by a large language model executed by the processor, the plurality of messages to extract a context of each message, (iii) determining, by the processor, a current context of interest to the user, (iv) identifying, by the processor, a subset of the plurality of messages that each comprises a context related to the current context of interest to the user, and (v) causing display, by the processor, of the subset of the plurality of messages in a digital message inbox.

Abstract: Disclosed embodiments are directed toward a computer-implemented system and method for providing an email digest in association with an interface display of an electronic inbox. The disclosed digest includes non-native inbox functionality related to a summary data structure that includes an interactive portion, whereby upon generation of electronic prompts via a large language model (LLM), the digest can leverage functionality of the LLM to determine how electronic inbox content can be rendered for display.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, electronic files stored in association with a user account, (ii) analyzing, by a large language model (LLM) executed by the processor, the electronic files and identifying, based on the LLM analysis, at least one file that is a candidate for deletion, (iii) compiling, by the processor, an electronic message comprising an output indicating deletion of the at least one file, (iv) causing display, by the processor, the electronic message, (v) receiving, by the processor, user input related to the at least one file, (vi) analyzing, by the LLM executed by the processor, the user input, and (vii) performing, by the processor based on the analysis of the user input via the LLM, an action on the at least one file conforming to the user input.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, an electronic message that comprises content generated by a user, (ii) predicting, by the processor, a potential action for the user by inputting the content of the electronic message into a large language model, (iii) suggesting, by the processor, the potential action to the user, (iv) receiving, by the processor, user input related to the potential action, and (v) performing, by the processor, on behalf of the user, a subsequent action conforming to the user input.

Abstract: The example embodiments are directed toward leveraging the power of large language models (LLMs) in a messaging application. In a first embodiment, LLMs are utilized to generate message content (both original and reply). In a second embodiment, LLMs are utilized to provide enhanced semantic search functionality. In a third embodiment, LLMs are utilized to provide intelligent actions to take based on message content.

Abstract: Disclosed are systems and methods for receiving a meeting request via an electronic account of a user; determining a conflict between the meeting request and a pre-existing meeting, extracting and comparing information associated with each meeting based on an analysis of each meeting; determining a priority associated with each meeting based on the analysis of the information of each meeting; and utilizing a machine learning model to generate an output associated with the priority of each meeting to the electronic account of the user.

Abstract: Example systems and methods provide input suggestions to a user to improve user experience on user devices. The input suggestions can be fill information from another app on device to the present app being used by user, information for performing a search (without the user having to copy-paste data or entering the data manually), responses to a message/notification received by the user, information/content/data to be shared between apps (without switching between apps), and emojis/GIFs that can be used by the user. The method includes analyzing one or more content of one or more screen displayed on device, generating at least one of a logical tree structure and a data mashup model of the one or more analyzed content for each screen, and providing a recommendation to a user. The recommendation can be a connected action or an input suggestion.

Abstract: Methods, systems, and devices for certification of device calibrations are described. Calibration information may be stored in a memory system having a cryptographic engine and included in the vehicle. An authentication platform may securely receive requests from a remote compliance device information associated with calibration for a vehicle that must be certified. The authentication platform may verify the identity of the compliance device and securely communicate a test authorization request to the vehicle. Compliance information pertaining to results of performing a compliance test for the vehicle may be subsequently communicated to the authentication platform.

Abstract: Described herein photonic interconnects based on glass interposers. Glass interposers of the types described herein are used to photonically interconnect multiple smaller photonic integrated circuits (PIC), as opposed to using a single, larger PIC. The typical yield of a glass interposer is significantly higher than the yield of a PIC. This is because glass interposers are passive in nature, while PICs include active photonic elements. Active photonic components (e.g., photonic transceivers and switches) tend to be more susceptible to manufacturing defects than passive photonic components (e.g., waveguides and couplers) because active components require additional manufacturing steps (e.g., ion implantation, sputtering, epitaxial growth, etc.). The approach described herein improves performance because instead of having to slice a large number of continuous reticles from a wafer, one can pick and choose reticles known to have yielded.

Abstract: Disclosed are systems and methods that provide a framework for machine-assisted discovery of Chondroitinase ABC (ChABC) complexes towards sustained neural regeneration. In some embodiments, the framework may leverage a determination of a diverse set of tailor-made random copolymers that complex and stabilize ChABC at physiological temperature. The copolymer designs, which are based on chain length and/or composition of the copolymers, may be identified using an active machine learning paradigm, which involves, but is not limited to, copolymer synthesis, testing for ChABC thermostability upon copolymer complexation, Gaussian Process Regression modeling and Bayesian optimization. Copolymers are synthesized by automated PET-RAFT, and thermostability of ChABC may be assessed by retained enzyme activity (REA) after a predefined interval of hours at 37° C.

Abstract: Systems and methods are disclosed for determining a visual indicator for a package based on a delivery address for the package and a location of the delivery address along a delivery route. An optimized delivery route may be created for packages to be delivered at a given time. At the fulfillment center, a delivery system may label a package prior to loading the package on a delivery vehicle. The delivery system may determine the appropriate visual indicator (e.g., color and/or pattern) or the visual indicator may be randomly selected. The delivery system may generate a label having the visual indicator. The package may be deposited into a certain bin with other packages having a delivery address in close proximity. The delivery system may generate a user interface on a user device that indicates that the package has a certain visual indicator to facilitate sorting and identification of the package.

Abstract: Systems, methods, models, and training data for models are discussed, for determining vehicle positioning, and in particular identifying tailgating. Simulated training images showing vehicles following other vehicles, under various conditions, are generated using a virtual environment. Models are trained to determine following distance between two vehicles. Trained models are used in detection of tailgating, based on determined distance between two vehicles. Results of tailgating are output to warn a driver, or to provide a report on driver behavior. Following distance over time is determined, and simplified following distance data is generated for use at a management device.