Abstract: Disclosed herein are systems and methods for improving the auto-generation of pipelined search query statements by a large language model (LLM) through novel processes for performing retrieval augmented generation (RAG). In some examples, such a method includes operations of receiving a natural language user-provided prompt, performing a first RAG process including retrieving first RAG data including natural language, programming syntax pairings from a vector database and performing a second RAG process including retrieving second RAG data including additional programming syntax examples from a vector database that have a second level of similarity with programming syntax of the natural language, programming syntax pairings retrieved during the first RAG process. The method may also include generating an auto-generated prompt requesting generation of programming code by a large language model (LLM) and generating a graphical user interface that displays the response to the auto-generated prompt from the LLM.

Abstract: Disclosed herein are systems and methods for improving the auto-generation of pipelined search query statements by a large language model (LLM). In some examples, such a method includes operations of receiving a user-provided prompt, wherein the user-provided prompt is provided in natural language, identifying an objective of the user-provided prompt, and based on the objective, providing the user-provided prompt to a first operational pipeline of a plurality of operational pipelines, wherein each operational pipeline is associated with a unique prompt template. Additionally, the method may include generating, by the first pipeline, an auto-generated prompt based on a first unique prompt template of the first pipeline, providing the auto-generated prompt to a large language model (LLM), and receiving a response to the auto-generated prompt from the LLM. A graphical user interface (GUI) may then be generated that displays the response to the auto-generated prompt.

Abstract: Disclosed herein are systems and methods for improving the auto-generation of pipelined search query statements by a large language model (LLM) through a post processing. In some examples, such a method includes operations of receiving, by a post processing engine, a response to an auto-generated prompt from the LLM that includes programming code generated by the LLM, performing a post processing of a response from the LLM that includes the programming code generated by the LLM including performing an error correction process when a term of the programming code generated by the LLM is inconsistent with terms of a schema of the user, and generating a graphical user interface (GUI) that displays the response to the auto-generated prompt when the terms of the programming code generated by the LLM including any replacement terms are consistent with the terms of the schema.

Abstract: A system includes a set of crawlers that find and retrieve documents from an information network, an information extraction system, a knowledge graph storing nodes and edges that connect them, wherein each node represents a respective entity of a corresponding entity type of a plurality of entity types, and wherein the knowledge graph further stores event data relating to events detected by the information extraction system, a machine learning system that trains models that are used in connection with at least one of entity extraction, event extraction, recipient identification, and content generation, a lead scoring system that scores the relevance of information to an individual and references information in the knowledge graph, and a content generation system that generates content of a personalized message to a recipient who is an individual for which the lead scoring system has determined a threshold level of relevance.

Abstract: The disclosure deals with a system and method for improved representation and retrieval of recipes or workflows. Recipes or workflows such as for preparing food or assembling furniture or performing other complex activities exist as textual or image documents, which makes it difficult for machines to read, reason, and handle ambiguity. The present disclosure provides a Rich Recipe Representation (“R3”), which is enhanced with additional knowledge such as outcomes like allergen information, possible failures, and solutions for each atomic step (such as a cooking step). The disclosed R3 is used in a web-based decision support system that helps users perform constrained queries using multiple modalities while also monitoring execution of an agent cooking or otherwise acting based on it.

Abstract: Embodiments disclosed herein are directed to devices, systems, and methods for separately processing an image stream to generate a first set of images for display by a set of displays and a second set of images for storage or transfer as part of a media capture event. Specifically, a first set of images from an image stream may be used to generate a first set of transformed images, and these transformed images may be displayed on a set of displays. A second set of images may be selected from the image stream in response to a capture request associated with a media capture event, and the second set of images may be used to generate a second set of transformed images. A set of output images may be generated from the second set of transformed images, and the set of output images may be stored or transmitted for later viewing.

Abstract: A data processing system includes: a server having a processor and a network interface; and a memory comprising programming instructions including a prompt generation engine. When executed by the processor, alone or in combination with other processors, the instructions cause the server to implement a service to: receive multiple media files from a presentation application on a client device; restructure content of the media files into a form compatible with a generative Artificial Intelligence (AI) tool; with the prompt generation engine, structure a prompt to the generative AI tool using the content of the media files in the form compatible with the generative AI tool, the prompt comprising an instruction to generate new content by fusing content from the multiple media files; receive the new content from the generative AI tool; and transmit the new content to the presentation application on the client device to augment a presentation being generated with the presentation application.

Abstract: A motor drive system is presented. The motor drive system may be configured to output a first, a second, and a third drive signal for driving an electric motor. The motor drive system may comprise a first power converter configured to generate the first drive signal, and a second power converter configured to generate the second drive signal. The motor drive system may comprise a third power converter configured to generate the third drive signal. Some or all of the power converters may be implemented as synchronous buck power converters.

Abstract: A structure for changing the attitude of a spacecraft is provided including an elongated member and a plurality of actuators coupled to the elongated member. The elongated member is coupled to the spacecraft. The elongated member has a length and an angular position relative to an axis. The plurality of actuators are configured to deflect the angular position of the elongated member relative to the axis and to alter the length of the elongated member.

Abstract: The present disclosure introduces a multi-panel structure designed to effectively attenuate sound transmission. The structure comprises a series of panels and absorbers arranged alternately. The panels are constructed from continuous and uninterrupted materials, with at least one panel incorporating a meta-material possessing metallic substance and specific properties. The absorbers feature porous materials with solid and fluid components, and in some cases, may also include meta-materials with solid and fluid components. The panels and absorbers possess optimized characteristics for sound attenuation, such as average bulk density, elastic modulus, and the damping ratio. Recycled materials can be utilized, promoting environmentally friendly construction without compromising sound-blocking capabilities.

Abstract: A method for determining whether in a communication channel within at least one multicore processor or multicore microcontroller, particularly within a vehicle, an anomaly is present. The at least one multicore processor or multicore microcontroller includes a plurality of cores. A communication between at least two of the plurality of cores is monitored, and based on a monitoring result, it is decided whether the anomaly is present or not.

Abstract: A system includes a set of crawlers that find and retrieve documents from an information network, an information extraction system, a knowledge graph storing nodes and edges that connect them, wherein each node represents a respective entity of a corresponding entity type of a plurality of entity types, and wherein the knowledge graph further stores event data relating to events detected by the information extraction system, a machine learning system that trains models that are used in connection with at least one of entity extraction, event extraction, recipient identification, and content generation, a lead scoring system that scores the relevance of information to an individual and references information in the knowledge graph, and a content generation system that generates content of a personalized message to a recipient who is an individual for which the lead scoring system has determined a threshold level of relevance.

Abstract: A system may include an object having a rotational axis. The system may also include a first mass movably mounted to the object and configured to adjust a moment of inertia of the object by translating relative to the object along an inertial path having a first component that is perpendicular to the rotational axis. The system may additionally include a second mass movably mounted to the object and configured to: apply to the object a first torque in a first direction along the rotational axis while the moment of inertia is adjusted above a threshold value and apply to the object a second torque in a second direction along the rotational axis while the moment of inertia is adjusted below the threshold value, by translating relative to the object along a torque path having a second component that is perpendicular to the rotational axis and the first component.

Abstract: Various arrangements for determining location suitability for satellite communication are presented herein. A mobile device can install an augmented reality (AR) application to output, via a display of the mobile device, a user interface depicting a field of view being captured by a camera of the mobile device. The AR application can capture, via the camera, one or more frames of an overhead area that collectively map a 360-degree representation of the overhead area. The one or more frames can be used to determine that continuous communication with a satellite constellation is available. The AR application can output, via the display, an obstruction map based on the one or more frames that indicates open sky available for communication with the satellite constellation.

Abstract: Embodiments disclosed herein are directed to devices, systems, and methods for separately processing an image stream to generate a first set of images for display by a set of displays and a second set of images for storage or transfer as part of a media capture event. Specifically, a first set of images from an image stream may be used to generate a first set of transformed images, and these transformed images may be displayed on a set of displays. A second set of images may be selected from the image stream in response to a capture request associated with a media capture event, and the second set of images may be used to generate a second set of transformed images. A set of output images may be generated from the second set of transformed images, and the set of output images may be stored or transmitted for later viewing.

Abstract: A structure for changing the attitude of a spacecraft is provided including an elongated member and a plurality of actuators coupled to the elongated member. The elongated member is coupled to the spacecraft. The elongated member has a length and an angular position relative to an axis. The plurality of actuators are configured to deflect the angular position of the elongated member relative to the axis and to alter the length of the elongated member.

Abstract: Embodiments disclosed herein are directed to devices, systems, and methods for separately processing an image stream to generate a first set of images for display by a set of displays and a second set of images for storage or transfer as part of a media capture event. Specifically, a first set of images from an image stream may be used to generate a first set of transformed images, and these transformed images may be displayed on a set of displays. A second set of images may be selected from the image stream in response to a capture request associated with a media capture event, and the second set of images may be used to generate a second set of transformed images. A set of output images may be generated from the second set of transformed images, and the set of output images may be stored or transmitted for later viewing.

Abstract: Implementations of this disclosure provide a machine learning model training system that receives user input being a natural language description of a search query, and packages and transmits the natural language description as a prompt to a plurality of large learning models (LLMs). The model training system also receives response from the plurality of LLMs being translations of the natural language descriptions to an executable search query and displays the translations to a user via a graphical user interface. The model training system receives user feedback via the graphical user interface that corresponds to indications as to whether each translation is correct, syntactically and/or semantically, and, in some examples, an indication of which response was preferred. The model training system also generates training data from the user input, translations generated by the plurality of LLMs, and user feedback, and subsequently, initiates training of a LLM using the training data.

Abstract: An example method for operating an energy recovery system may comprise providing a reducing gas stream to an inlet of the energy recovery system, contacting redox particles with the reducing gas stream, whereupon the at least one reducing gas species undergoes a chemical reaction with the redox particles to generate carbon dioxide (CO2) and/or steam (H2O) obtaining a first product stream from the energy recovery system, providing an oxidizing gas stream comprising steam (H2O) to the energy recovery system such that hydrogen gas (H2) is generated, and obtaining a second product stream from the energy recovery system, the second product stream comprising hydrogen gas (H2). The reducing gas stream may comprise at least one reducing gas species comprising at least one of carbon monoxide (CO), methane (CH4), hydrocarbons (C2+), hydrogen gas (H2), and carbon dioxide (CO2). The first product stream may comprise carbon dioxide (CO2) and steam (H2O).

Abstract: Exemplary reactor systems may include multiple reactors in fluid communication. Oxygen carrier particles comprising a support material and metal oxide can be provided to a first reactor along with flue gas comprising carbon dioxide (CO2). An output of the first reactor is free or substantially free of carbon dioxide (CO2). The oxygen carrier particles can then be provided to one or more reactors in the system along with a hydrocarbon stream and, in some instances, an oxidizing stream. Outlets from these one or more reactors may include hydrogen gas (H2), carbon monoxide (CO), and/or other species, depending upon the content of the hydrocarbon streams and the oxidizing streams.