Abstract: A data processing system implements obtaining device information and performance requirements information for a resource-constrained computing device; analyzing the device information and the performance requirements information to determine an amount to compress one or more machine learning models to permit the resource-constrained computing device to operate the one or more machine learning models on the resource-constrained computing device, the one or more machine learning models including a stroke classification model for classifying digital ink stroke information as handwriting or a drawing; compressing the one or more machine learning models to permit the one or more machine learning models to operate on the resource-constrained computing device to generate one or more compressed machine learning models; and deploying the one or more compressed machine learning models to the resource-constrained computing device to process ink stroke information captured by a user interface of the resource-constrained

Abstract: Examples of the present disclosure describe systems and methods for automatically assisting conversations using a graph database. In order to minimize misunderstanding of words and phrases used by participants during a conversation, phrases from the conversation may be received by conversation assistance application as the conversation takes place. Entities may be extracted from the phrase based on natural language recognition according to a domain context of the participant being assisted. One or more tags may be looked up from a graph database, and may be provided to the participant as a list of hashtags related to the conversation. Links to documents may be extracted based on the tags for the participant for viewing during the conversation.

Abstract: A method for annotating images to create a corpus for training a multi-task computer vision machine learning model is presented. The method comprises receiving, at one or more annotation specialist models, a plurality of images to be annotated. Via operation of the one or more annotation specialist models, pre-filtered annotations are generated for the plurality of images. Via operation of a data filtering and enhancement module, the pre-filtered annotations are filtered in accordance with predefined noise criteria so as to output candidate annotations for the plurality of images. The method further comprises, for each of one or more candidate annotations, selectively (1) storing the candidate annotation into the corpus as a final annotation for its associated image, or (2) adding the candidate annotation to its associated image using the one or more annotation specialist models and the data filtering and enhancement module for subsequent iterative annotation and filtering.

Abstract: A data processing system implements obtaining build logs that include information associated with a software build problem; analyzing the logs to generate a knowledge graph identifying the relationship between various entities in the logs; extracting a signature of a candidate root cause of the build problem from the knowledge graph representing a subset of nodes and edges of the knowledge graph; providing the signature of the candidate root cause to a graphical language model to obtain a prediction of a category of root cause failure selected from among a plurality of root cause failures; constructing a prompt for a language model to generate a root cause failure analysis that describes the root cause of the build problem, the prompt including the category of root cause; receiving the root cause failure analysis from the language model; and performing one or more actions in response to receiving the root cause failure analysis.

Abstract: Examples are disclosed that relate to fans configured to automatically adjust for imbalances in mass. One example provides a self-balancing fan, comprising a hub comprising a plurality of blade interfaces, and a plurality of blade structures each attached to a corresponding blade interface of the hub, each blade interface comprising a tapered notch in the hub and being configured to increase a balancing force exerted by the hub against the blade structure as a function of increasing distance of the blade structure from the hub.

Abstract: A device includes: a processor, and a memory storing executable instructions which, when executed by the processor, causes the processor, alone or in combination with other processors, to provide the following: a user interface comprising administrator access to a collaboration system, the user interface comprising a control to invoke an artificial intelligence (AI) assistant function; and an Application Programming Interface (API) to, in response to activation of the control, download user activity data for the collaboration system, generate a prompt for a Large Language Model (LLM) comprising the user activity data and instructing the LLM to generate a report based on the user activity data, and submit the prompt to the LLM and receive the report generated by the LLM. The user interface provides the report and controls for administrative actions suggested by the report.

Abstract: The disclosed concepts relate to contextualization of generative language models. In some implementations, a linked entity database is populated with entity resource identifiers of entities extracted from a search log by an entity linker. A contextualized prompt data structure is generated based on the linked entity database, e.g., by including linked entity context information in the contextualized prompt data structure. A response to the contextualized prompt data structure is received, where the response is conditioned on the linked entity context information.

Abstract: In non-limiting examples of the present disclosure, systems and methods are described that relate to providing, in a browser environment, a sidebar search capability to users. Once in a primary content page, the user is able to select text for searching. In response, the system provides a context menu or keyboard shortcut that includes an option for conducting a sidebar search. In response to user selection, the system passes highlighted or selected text as a parameter to the search engine. The results are provided in an area alongside the currently displayed content page, such as in a sidebar search pane. The user is able to experience search results without leaving the context of their current search tab.

Abstract: Methods, systems, apparatuses, and computer program products are provided for enabling access to a resource in a secured manner. A token request from an application executing in a first computing environment may be received in a second computing environment. The second computing environment may assign a trust level to the received token request that indicates that the first computing environment may not be trusted. The token request, along with the trust level, may be provided to an authorization server to generate an authorization token that includes a trust indication indicative of the trust level of the second computing environment. When the application executing in the second computing environment transmits the authorization token to a resource manager to access a resource, the resource manager may be configured to perform a precautionary action to protect the resource prior to providing access, such as creating a backup of the resource.

Abstract: Techniques are described herein that are capable of using a requestor identity to enforce a security policy on a network connection that conforms to a shared-access communication protocol. A request to create the network connection to a network resource is received. The network connection is associated with the requestor identity, which identifies a requesting entity associated with the request, by associating the request with the requestor identity and further by associating the network connection with the request. A determination is made whether the requesting entity is authorized to access the network resource based at least in part on a permission that is indicated by the security policy. Based at least in part on the permission indicating that the requesting entity is authorized to access the network resource, the network connection to the network resource is created.

Abstract: A fabric control protocol (FCP) and packet forwarding mechanisms are described that maximize utilization of bandwidth within massive, large-scale data centers having multi-stage data center switch fabric topologies, such as topologies that include a third switching layer formed by super spine switches. Automatic generation of data plane forwarding information referred to as FCP path information enumerates, for each data processing unit (DPU), the available FCP paths. The FCP path information may be based on unique combinations of peak points of the switch fabric for a given DPU with FCP colors assigned to network links that are used to multi-home the DPU to the switch fabric.

Abstract: Various implementations of the present disclosure relate to style transfer. In some implementations, a computer-implemented method comprises: obtaining a target object having a first style, a style of the target object being editable; obtaining a reference image including a reference object; obtaining a second style of the reference object, the second style of the reference object being extracted from the reference image; and applying the second style to the target object.

Abstract: In various examples, there is a method of enabling an attestable update of a firmware layer that provides a unique identity of a computing device. An immutable firmware layer is used to access a unique device secret. The immutable layer is used to derive a hardware device identity (HDI) from the unique device secret. The immutable layer is used to derive a compound device identity (CDI) from a measurement of the firmware layer and the unique device secret. The CDI and HDI are made available to the firmware layer. The firmware layer is used to issue a local certificate to endorse a device identity key, derived from the CDI, the local certificate signed by a key derived from the HDI.

Abstract: Systems and methods for reconfiguring application windows in a display. An example method includes displaying a first application window and a second application window; receiving a drag input for moving the first application window; based on the drag input entering an invocation region, displaying a layout menu with a plurality of display layouts, each of the display layouts including one or more snap zones; receiving a hover of the first application window over a particular snap zone of a particular display layout of the plurality of display layouts; based on the hover of the first application window over the particular snap zone, displaying a zone-indicator pane corresponding to the particular snap zone; receiving a drop input of the first application window over the particular snap zone; and in response to the drop input, resizing and repositioning the first application window according the particular snap zone.

Abstract: A function processing service may receive a request to execute source code. The source code may include instructions to perform a function. The function processing service may determine whether at least one hardware acceleration condition has been satisfied for the function. If at least one hardware acceleration condition has been satisfied, the instructions in the source code may be translated into hardware-specific code corresponding to a hardware circuit. The hardware circuit may be configured based on the hardware-specific code, and the hardware circuit may perform the function. The function processing service may then provide the result obtained from the hardware circuit to the requesting entity.

Abstract: The techniques disclosed herein provide controlled user interface transitions for private breakout communication sessions. A system provides a Together Mode user interface that gives participants of a communication session a feeling that they are in the same room. When a person joins a communication session, a system uses a seating policy to determine a location of that user. That user is placed near or next to a select user. A policy is applied when users meet one or more conditions. If a number of people join the communication session, each person is ranked according to an organizational chart and each person is positioned and ordered relative to the select user according to each person's rank. The system configures the updated user interface arrangement to maintain the position of the select group of the participants.

Abstract: A video pass-through computing system includes a head-mounted display device including a display, a camera configured to image a physical scene according to an exposure timing, and an augmented reality control circuit configured to receive a virtual image pixel stream and composite the camera image pixel stream with the virtual image pixel stream to generate a display image pixel stream output to the display, and if a corresponding pixel of the camera image pixel stream is not in temporal synchronization with a pixel of the virtual image pixel stream adjust the exposure timing of the camera.

Abstract: Solutions for data unification include: receiving a data record, the data record comprising a plurality of data fields; selecting, from among the plurality of data fields, a subset of the data fields, the subset of the data fields being fewer in number than the plurality of data fields, wherein selecting the subset of the data fields comprises: applying a first rule to select at least a first one of the data fields within the data record for inclusion in the subset of the data fields; using content of the subset of the data fields, generating a stable identifier (stableID) for the data record; and inserting the stableID into a primary key data field of the data record.

Abstract: The present disclosure relates to systems, methods, and computer-readable media for receiving usage data for a virtual device (or other virtual service), analyzing the usage data to determine a usage bucket characteristic of usage of the virtual device over a period of time, and determining a usage score for the virtual device. The systems described herein further involve causing a deployment of the virtual device to be upgraded, downgraded, or otherwise modified based on the usage bucket and associated usage score. The features and functionalities described herein can provide an efficient mechanism for administrating a tenant deployment as well as implementing a more efficient utilization of cloud computing resources for a variety of virtual services.

Abstract: A computing system obtains text that includes words and provides the text as input to an emotional classifier model that has been trained based upon emotional classification. The computing system obtains a textual embedding of the computer-readable text as output of the emotional classifier model. The computing system generates a phoneme sequence based upon the words of the text. The computing system, generates, by way of an encoder of a text to speech (TTS) model, a phoneme encoding based upon the phoneme sequence. The computing system provides the textual embedding and the phoneme encoding as input to a decoder of the TTS model. The computing system causes speech that includes the words to be played over a speaker based upon output of the decoder of the TTS model, where the speech reflects an emotion underlying the text due to the textual embedding provided to the encoder.