Abstract: Embodiments of the disclosed technologies include receiving a first query including at least one first query term and configuring at least one prompt to cause a large language model to translate the at least one first query term into a set of functions that can be executed to obtain at least one second query term and generate and output a plan that is executable to create a modified version of the first query based on the at least one second query term. The plan is obtained by applying the large language model to the at least one prompt as configured. The plan is executed to determine the at least one second query term and create the modified version of the first query. The modified version of the first query is executed to provide, via the user interface, a response to the first query.

Abstract: Techniques for creating an interest graph include obtaining content items from multiple content sources and applying tailored (e.g., source-specific) preprocessing to the content items based on their respective content source. Text is extracted and salient keywords and key phrases are identified using unsupervised machine learning models. The keywords and key phrases become nodes in an interest graph, each node comprising an embedding of a keyword or key phrase in a common embedding space, with edges representing semantic similarity based on embeddings or co-engagement patterns. The graph provides an expansive, granular, and dynamic taxonomy easily adaptable to emerging interests. The interest graph overcomes limitations of conventional taxonomies that lack depth, fail to capture niche interests, and cannot adapt to reflect evolving user preferences. The described techniques construct a rich interest graph from diverse content for improved content understanding.

Abstract: A method and a system for automatically generating one or more real time updates for at least one live event is described. In one example, a processing unit is connected to a storage unit and a display unit, said processing unit fetches a content stream of the at least one live event and identifies at least one moment from the content stream. Based on the identified moment, at least one real time update is generated by the processing unit. The generated real time updated is then displayed on the display unit.

Abstract: An advanced metering infrastructure includes a smart meter system with at least one sensor, a communication device, and a battery supply. The smart meter system is provided with algorithms and configuration to improve wireless connection reliability on the smart meter by providing more than one mobile operator configuration and more than one modem stacks for respective mobile network operators. When a mobile connection becomes unavailable, the system may automatically or manually change a mobile network operator and/or modem stack in hopes that communication quality and connection availability improves.

Abstract: Techniques for automated tagging of visual content are described. A pairwise model is used to encode images and videos with a vision encoder, and encode keywords and phrases from an interest graph with a text encoder. Similarity layers compare these cross-modality embeddings by calculating distance in a shared embedding space. Scores indicate the association between visual features and text. A pairwise loss function brings together matched pairs while separating non-matches during training. Scores exceeding a threshold tag content with relevant keywords and phrases. The pairwise architecture relates images and text despite limited associated text. It leverages vision-to-text understanding for accurate tagging without per-class labels. Contrastive similarity techniques associate visual patterns with textual concepts. Automated tagging organizes user-generated content by topics using this scalable cross-modality approach.

Abstract: Various examples of improving an in-memory graph query engine using a persisted storage component are provided. The method includes updating data stored in an in-memory graph query engine and, based on updating the data, converting the data to a plain text form that may be more efficiently stored in the persistent storage component. The method further includes updates to additional in-memory graph query engines from the persistent storage component such that in-memory data stored in the graph query engines is synchronized.

Abstract: Systems, methods, and computer program products for identifying zones of interest in text transcripts. An application may receive input specifying a text statement type and determine a plurality of heuristics for identifying statements of the statement type in transcripts. The application may determine, based on a first heuristic, a first text statement of the statement type. The application may generate, based on a clustering algorithm, a plurality of additional statements of the statement type. The application may receive a first text transcript. The application may identify, based on a second heuristic, a first text statement in the first text transcript, where the first text transcript statement is of the statement type. The application may generate a graphical indication that the first text transcript statement is of the statement type, and display the first transcript statement and the graphical indication on a display.

Abstract: An in-silicon monitoring circuit for an on-chip static RAM (SRAM) is disclosed. In one embodiment, the on-chip static RAM comprises a clock generation unit and an SRAM ring oscillator (RAMRO) output circuit. In one embodiment, the clock generation unit includes a multiplexer with inputs that include a clock signal a reset signal provided by a delay chain of the SRAM, where the multiplexer is controlled by an enable signal (RAMRO_EN). In one embodiment, the RAMRO output circuit that generates a RAMRO output signal (RAM_RO) based on the RAMRO_EN signal and an input from the delay chain of the SRAM when the RAMRO_EN signal is asserted, where the RAMRO output signal correlates to electrical characteristics of semiconductor material upon which the SRAM is located.

Abstract: Aspects of the disclosure are directed to peak current mitigation. In accordance with one aspect, the disclosure includes managing a plurality of peak current events based on a plurality of peak current detection messages to generate a management plan; and mitigating the plurality of peak current events using a plurality of mitigation actions from the management plan. And, the disclosure includes a processing engine configured to perform general purpose processing; and a power management integrated circuit (PMIC) coupled to the processing engine, the PMIC configured to manage a plurality of peak current events associated with the processing engine based on a plurality of peak current detection messages to generate a management plan, and configured to mitigate the plurality of peak current events using a plurality of mitigation actions from the management plan.

Abstract: Aspects of the subject technology relate to power consuming processes of electronic devices. For example, an electronic device may create, initiate, and/or modify a power consuming process of the electronic device, based in part on user power consumption information that indicates a typical amount of power consumed by a user of the electronic device. The electronic device may recommend increases in power consumption for low power consumption users and/or decreases in power consumption for high power consumption users. A power consumption process may include a visual arrangement of graphical elements that each display periodically, occasionally, and/or continuously updated information from the application, when a full user interface of the application is not displayed.

Abstract: A method for on-demand registration of whole slide images (WSIs), comprising receiving at least two digital images, a first digital image of a reference slide and a second digital image on a candidate slide, each at a first magnification level, identifying a first region of interest (ROI) on the first digital image at a target magnification level, registering a portion of the second digital image to a portion of the first digital slide image at the first magnification level to derive a transformation matrix, applying the transformation matrix to the first ROI to identify a second ROI on the second digital image at the first magnification level, mapping the second ROI to a corresponding second ROI on the second digital image at the target magnification level, and registering the corresponding second ROI to the first ROI at the target magnification level.

Abstract: A cell for an optical cavity includes a tube with a first open-end and a second open-end, a first end-cap, and a second end-cap. The first end-cap is fixedly attached to the tube at the first open-end and has an opening with a center axis. The second end-cap is fixedly attached to the tube at the second open-end and has an opening with a center axis that is axially aligned with the center axis of the first end-cap.

Abstract: Automated attribute scraping for security feature implementation with a single trained machine model across security features improves prediction quality and efficiency of predictions. A security feature implementation prediction system (system) generates search engine queries for each security feature based on high importance tokens for the security feature. The system ranks URLs returned from each search engine query for relevance, then preprocess and inputs content for top-ranked URLs into the trained machine learning models. The system identifies implemented security features output based on confidence values output by the trained machine learning model and identifies sentences that describe the implementations in corresponding content for top-ranked URLs.

Abstract: In some implementations, a system is provided for securely transferring access credentials from a mobile device that is exclusively operated by a single user, to a terminal device that is shared among multiple different users, via a session server. A session is established between the session server and the terminal device over a secure communication channel. The terminal device generates a key pair, transmits the public key to the session server, and stores the private key. The terminal device outputs a detectable code corresponding to the session. In response to detecting the detectable code, the mobile device transmits an access token payload to the session server. The session server transmits, to the terminal device, an encrypted access token that has been encrypted using the public key. The terminal device decrypts the encrypted access token using the stored private key, and provides operator access to the terminal device.

Abstract: A method and system for classifying a triage-related message related to a software application security technical problem is provided. A triage-related classification is generated for the triage-related message by applying a processor-implemented machine learning model that has been trained to analyze the text of the triage-related message. The generated triage-related classification is sent to a user for remediating the software application security technical problem.

Abstract: Disclosed herein are an integrated circuit die stack and an integrated circuit die package assembly having the integrated circuit die stack. The integrated circuit die stack includes a plurality of integrated circuit dice disposed in a first tier of the die stack and a plurality of integrated circuit dice disposed in a second tier of the die stack. The plurality of integrated circuit dice of the second tier are stacked vertically above the plurality of the integrated circuit dice of the first tier and include a bridge die. The bridge die couples with at least two dice of the first tier and includes an integrated passive device coupled with a routing connection.

Abstract: A technique detects latency-related anomalies that occur in performing provisioning actions in a network-accessible computing platform. Illustrative provisioning actions include creating a resource (e.g., a virtual machine), updating the resource, and deleting the resource. The technique operates by detecting and reporting the latency-related anomalies on a service-level granularity. The technique also provides access to operation-level latency-related data to assist in diagnosing the causes of the anomalies. In some implementations, the technique consolidates incidents that potentially reveal a common source of failure into a single report. In some implementations, the technique interacts with a machine-trained language model to confirm whether a reported incident is a false positive which does not warrant further action.

Abstract: A system is adapted to automatically report the trustworthiness of an entity. The system includes a processor and a computer readable medium carrying instructions. The instructions include receiving unstructured data pertaining to an entity from public sources, and receiving structured data pertaining to the entity from at least two databases. The instructions also include merging the structured data and the unstructured data into a single document; splitting the single document into chunks; creating embeddings corresponding to the chunks; and storing the embeddings in a vector store. The instructions also include receiving a natural language user query regarding trustworthiness of the entity; converting the query to a query embedding; based on the query embedding and a similarity calculation, fetching a relevant embedding from the vector store; with a large language model (LLM), generating a query response regarding the trustworthiness of the entity; and communicating the query response to the user.

Abstract: Log events for a target system are received. In each of a number of iterations, selection of a filter from a library of preexisting filters is received from a user, the selected filter is applied to the log events to generate filtered log events, and the filtered log events are displayed to the user. In each iteration other than a first iteration, the selected filter is applied to the filtered log events that are generated in an immediately preceding iteration.