Abstract: The technology relates to systems and methods for dynamically generating prompts for a generative artificial intelligence (AI) model. An example method includes receiving input content for evaluation by a generative AI model; receiving an input-content embedding for the input content; receiving trait data and trait-data embeddings for the trait data; identifying similar trait data by comparing the input-content embedding with the trait-data embeddings, wherein the similar trait data is a subset of the trait data that is similar to the input content; generating a prompt including the input content and the identified similar trait data; providing the prompt to the generative AI model; and receiving, from the generative AI model in response to the prompt, an output payload including an evaluation of the input content.

Abstract: The disclosed concepts relate to leveraging a language model to identify data health issues in a data set. One example method involves accessing a data set. The example method also involves, using an automated evaluation planning agent, inputting a prompt to generate a data evaluation plan for the data set to a generative language model, the prompt including context describing the data set. The example method also involves receiving the data evaluation plan generated by the generative language model and identifying one or more data health issues in the data set by performing the data evaluation plan using an automated evaluation plan execution agent.

Abstract: Disclosed herein are exemplary embodiments of methods, apparatus, and systems for performing content-adaptive deblocking to improve the visual quality of video images compressed using block-based motion-predictive video coding. For instance, in certain embodiments of the disclosed technology, edge information is obtained using global orientation energy edge detection (“OEED”) techniques on an initially deblocked image. OEED detection can provide a robust partition of local directional features (“LDFs”). For a local directional feature detected in the partition, a directional deblocking filter having an orientation corresponding to the orientation of the LDF can be used. The selected filter can have a filter orientation and activation thresholds that better preserve image details while reducing blocking artifacts. In certain embodiments, for a consecutive non-LDF region, extra smoothing can be imposed to suppress the visually severe blocking artifacts.

Abstract: Some embodiments provide a notebook tool enhanced with minimoremap functionality. Notebooks are multicell documents with varied mime types present in the content of various cells of a given notebook, including executable source code such as scripts, non-executable content, markdown text, natural language text, photos, videos, maps, and more. The notebook tool includes a main view and a superimposed minimoremap view which is functionally coordinated with the main view, e.g., for navigation and cell selection. Notebook cell operations are commanded via the minimoremap. Cells outside the main view viewport are modified without changing the user interface main view focus. Tool-human interaction commands cause the performance of notebook operations such as cell execution, cell rearrangement, cell collapse, cells merge, cells grouping, or cell dependency analysis. Minimoremap cell images are rendered as icons, as graphics, or as scaled-down versions of previously rendered full-size main view images.

Abstract: A laser device for use with a display including a plurality of pixels is disclosed. The laser device includes a gain section and a modulator. The gain section is electrically coupled with a first current or voltage source. The gain section is configured to selectively amplify an optical power of light reflecting within the gain section based on a first drive current or voltage supplied from the first current or voltage source to the gain section. The modulator is optically coupled with the gain section. The modulator is electrically coupled with a second current or voltage source. The modulator is configured to selectively attenuate or amplify an optical power of light received from the gain section based on a second drive current or voltage supplied from the second current or voltage source to the modulator. Light emitted from the modulator is provided to the display.

Abstract: A data processing system implements a receiving a textual input comprising a query for a first image. The data processing system also implements analyzing the textual input to determine a predicted color palette associated with a subject matter of the query; and procedurally generating the first image using the predicted color palette. Another implementation of the data processing system implements providing the textual input to a first machine learning model to obtain the first image, the first machine learning model being trained using a dataset comprising abstract imagery and analyzing the textual input using the first machine learning model to obtain the first image in response to receiving the textual input.

Abstract: The interactive and shared surface technique described herein employs hardware that can project on any surface, capture color video of that surface, and get depth information of and above the surface while preventing visual feedback (also known as video feedback, video echo, or visual echo). The technique provides N-way sharing of a surface using video compositing. It also provides for automatic calibration of hardware components, including calibration of any projector, RGB camera, depth camera and any microphones employed by the technique. The technique provides object manipulation with physical, visual, audio, and hover gestures and interaction between digital objects displayed on the surface and physical objects placed on or above the surface. It can capture and scan the surface in a manner that captures or scans exactly what the user sees, which includes both local and remote objects, drawings, annotations, hands, and so forth.

Abstract: A reference to a digital item is stored as a digital card. The digital card can also be contained in, and/or refer to, other digital cards. The digital card can also include properties or attributes that may be added from the digital item that is being referred to. The digital card can be tagged with a tag that may also be applied to other digital cards. The digital card can be stored in a data pod within a de-centralized data storage system architecture so the tag is surfaced along with the digital card in different contexts.

Abstract: In implementations of the subject matter as described herein, there is provided a method for forgery detection of a face image. Subsequent to inputting a face image, it is detected whether a blending boundary due to the blend of different images exists in the face image, and then a corresponding grayscale image is generated based on a result of the detection, where the generated grayscale image can reveal whether the input face image is formed by blending different images. If a visible boundary corresponding to the blending boundary exists in the generated grayscale image, it indicates that the face image is a forged image; on the contrary, if the visible boundary does not exist in the generated grayscale image, it indicates that the face image is a real image.

Abstract: Disclosed in some examples are methods, systems, devices, and machine-readable mediums which provide for sidebar communication threads forked from, or related to, a principal thread. Messages in the sidebar communication thread may include a history of the principal thread, including one or more messages from the principal thread, and may include a proposed principal thread message that is the subject of the sidebar thread discussion. The sidebar thread may also include sidebar thread messages that carries the conversation of the sidebar thread participants. Once a termination condition is reached for the sidebar thread, the sidebar thread terminates and either the proposed principal thread message (as potentially modified by participants of the sidebar thread) becomes an accepted principal thread message and it is posted to the principal thread as if it was sent by the sidebar initiator or no message is posted (e.g., the proposed principal thread message is rejected).

Abstract: Generally discussed herein are examples of gesture-based extended reality (XR) with object recognition and tracking. A method, implemented by an extended reality (XR) device can include recognizing and tracking one or more objects in the image data, recognizing a gesture in the image data, analyzing the image data to determine whether a condition is satisfied, the condition indicating a recognized and tracked object of the one or more objects proximate which the recognized gesture is to be made, and in response to determining that the condition is satisfied, performing an augmentation of the image data based on satisfaction of the condition.

Abstract: A method of writing voxels to a substrate using a laser writing system comprises forming a first voxel at a first position in a substrate using a first laser pulse; detecting light emitted or scattered by the substrate as a result of forming the first voxel; determining whether the detected light satisfies a predetermined constraint; and, when the detected light does not satisfy the predetermined constraint, adjusting an amplitude of a second laser pulse. Light emission or scattering from the substrate as a result of forming a voxel is related to the properties of the formed voxel. By monitoring such emission or scattering, it is made possible to compensate for variations in performance of the laser writing system. Also provided herein are a laser writing system and computer program product which implement the method.

Abstract: Methods, systems, and computer program products for direct assignment of physical devices to confidential virtual machines (VMs). At a first guest privilege context of a guest partition, a direct assignment of a physical device associated with a host computer system to the guest partition is identified. The guest partition includes the first guest privilege context and a second guest privilege context, which is restricted from accessing memory associated with the first guest privilege context. The guest partition corresponds to a confidential VM, such that a memory region associated with the guest partition is inaccessible to a host operating system. It is determined, based on a policy, that the physical device is allowed to be directly assigned to the guest partition. Communication between the physical device and the second guest privilege context is permitted, such as by exposing the physical device on a virtual bus and/or forwarding an interrupt.

Abstract: A system for dark current compensation in SPAD imagery is configurable to capture an image frame with the SPAD array and generate a temporally filtered image by performing a temporal filtering operation using the image frame and at least one preceding image frame. The at least one preceding image frame is captured by the SPAD array at a timepoint that temporally precedes a timepoint associated with the image frame. The system is also configurable to obtain a dark current image frame. The dark current image frame includes data indicating one or more SPAD pixels of the plurality of SPAD pixels that detect an avalanche event without detecting a corresponding photon. The system is also configurable to generate a dark current compensated image by performing a subtraction operation on the temporally filtered image or the image frame based on the dark current image frame.

Abstract: A client-side system detects a current location of a client device and a cloud interaction metric. The geographic area around the location of the client device is divided into grid sections. The client-side system identifies a pre-defined reference location corresponding to the grid section that the client device location resides in. The pre-defined reference location, corresponding to that grid section, and the cloud interaction metric are provided to a remote server computing system.

Abstract: Methods, systems, and computer programs are presented for eliminating bias while training an ML model using training data that includes past experimental data. One method includes accessing experiment results, for A/B testing of a first model, that comprise information regarding engagement with a first set of items presented to users, each item being presented within an ordered list of results. A position bias is calculated for positions within the ordered list of results where the items were presented. A machine-learning program is trained to obtain a second model using a training set comprising values for features that include the calculated position bias. The method includes detecting a second set of items to be ranked for presentation to a first user, and calculates, using the second model, a relevance score for the second set of items, which are ranked based on the respective relevance score and presented on a display.

Abstract: A method, computer program product, and computing system for generating a first synthetic dataset including a synthetic transcription and a corresponding natural dictation record using a first machine learning model trained to generate transcriptions from medical records. A second synthetic dataset including a synthetic medical record and a corresponding natural transcription is generated using a second machine learning model trained to generate medical records from transcriptions. The first synthetic dataset and the second synthetic dataset are combined with a natural dataset into a synthetic training dataset.

Abstract: A computing system is configured to detect a request for a deployment of a container at a container orchestration service. One or more datasets associated with the deployment of the container are collected, and a plurality of features associated with the deployment are extracted based on the one or more datasets. A probability score is then generated based on the plurality of features, using a machine-learning model trained on datasets associated with historical deployments of containers that have been performed via the container orchestration service. The probability score indicates a probability that the deployment of the container is anomalous compared to the historical deployments of containers. When the probability score is greater than a threshold, the deployment of the container is determined as anomalous.

Abstract: A solution is disclosed for computer hardware replacement using performance analytics that selects replacement computer hardware based on actual user needs and enterprise priorities. Key performance data is collected and compared with various baselines, thereby identifying hardware that is performing below acceptable levels. Enterprise data and collected data are received from an instrumented operating system on a computing device. The collected data includes boot performance, application performance, and hardware performance. Based at least on the collected data, a usability score is determined by performing a weighted calculation on the collected data. Based at least on the usability score and the enterprise data, it is determined whether a score improvement is required. Based at least on the enterprise data, a score improvement selection is determined. The score improvement selection is reported based at least on determining that a score improvement is required.

Abstract: A method for generating speech through multi-speaker neural text-to-speech (TTS) synthesis is provided. A text input may be received (1410). Speaker latent space information of a target speaker may be provided through at least one speaker model (1420). At least one acoustic feature may be predicted through an acoustic feature predictor based on the text input and the speaker latent space information (1430). A speech waveform corresponding to the text input may be generated through a neural vocoder based on the at least one acoustic feature and the speaker latent space information (1440).