Abstract: In accordance with some embodiments, systems, methods, and media for improving signal-to-noise ratio in single-photon data are provided. In some embodiments, a system comprises: a processor programmed to: generate, for each of a plurality of pixel locations, initial photon flux estimates based on a first set of photon transients including photon transients associated with the pixel location and neighboring pixel locations, each of the photon transients comprises a histogram of photon counts; identify, for a scene patch associated with each of the plurality of pixel locations, one or more similar scene patches using intensity information for each of the plurality of pixel locations; and generate, for each of the plurality of pixel locations, final photon flux estimates based on a second set of photon transients including photon transients associated with the scene patch and each of the one or more similar scene patches.

Abstract: In accordance with some embodiments, systems, methods, and media for estimating a depth and orientation of a portion of a scene using a single-photon detector and diffuse light source are provided. In some embodiments, a system comprises: a light source; an image sensor comprising a pixel having a field of view of at least one degree; a hardware processor programmed to: cause the light source to emit a sequence of n defocused pulses toward the scene; receive, from the pixel, information indicative of arrival times of light from the scene; generate a transient histogram using the information indicative of arrival times of light from the scene; and estimate one or more properties of a portion of the scene within the field of view of the pixel based on the transient histogram, wherein the one or more properties of the portion of the scene includes at least a depth.

Abstract: A computing system includes at least one processing circuit having at least one processor and at least one memory device. The processing circuit performs operations including: providing a chat interface to allow a plurality of travelers to initiate a chat session in which the plurality of travelers collaborate to plan a trip; receiving, via the chat session, input from the plurality of travelers related to the trip; and automatically interacting, via a chatbot, with the plurality of travelers within the chat session to plan the trip by: processing, using a machine learning model, a content of the chat session to generate one or more recommendations for the trip, wherein processing the content of the chat session includes generating the one or more recommendations using the input from the plurality of travelers; and providing the generated one or more recommendations to the plurality of travelers within the chat session.

Abstract: Embodiments disclosed herein include package substrates with bridge dies. In an embodiment, an apparatus comprises a first layer that is a glass layer. A via is provided through the first layer, where the via is electrically conductive. In an embodiment, a second layer is over the first layer, and the second layer comprises an organic dielectric material. In an embodiment, a cavity is provided in the second layer, where the via is within a footprint of the cavity. In an embodiment, a die is in the cavity. In an embodiment, the die is electrically coupled to the via.

Abstract: An example memory circuit includes a memory cell coupled to a first row line, a second row line, a first bit line, and a second bit line, the first bit line and the second bit line coupled to a first node of the memory cell, the memory cell configured to store a bit; and a controller including a first write driver coupled to the first bit line and a second write driver coupled to the second bit line, the first write driver configured to, during a first time interval, apply a first voltage to the first bit line in response to a first control signal and a first data signal, the second write driver configured, during the first time interval, to apply the first voltage to the second bit line in response to a second control signal and the first data signal.

Abstract: Methods and systems for processing frame data are disclosed. The methods and systems include: obtaining a sequence of data, the sequence comprising at least a first frame; applying the sequence of data to a machine learning model; and providing an inference result based on the machine learning output score from the machine learning model. The machine learning model is configured to: determine at least one token-level error based on a difference between at least one token of a first representation corresponding to the first frame and a second representation; perform a first transformer operation based on the token subset to produce an output representation corresponding to the token subset; scatter the output representation to a buffer representation corresponding to the first representation; and produce a machine learning output score based on the buffer representation. Other aspects, embodiments, and features are also claimed and described.

Abstract: Monitoring write amplification metrics for a flash-based storage system, including: generating, by a controller of a storage system, data describing write activity for each storage device of a plurality of storage devices of the storage system, wherein the data describing the write activity comprises data describing application write activity for each storage device of the plurality of storage devices; calculating, by the controller of the storage system, for each storage device of the plurality of storage devices, a corresponding write amplification metric; and providing, by the controller of the storage system, to each storage device of the plurality of storage devices, the corresponding write amplification metric.

Abstract: A system and method for quanta sensing is provided. The system includes a quanta sensor, a neutral atom, collection optics, quantum computer, a processor, and a memory. The memory includes instructions stored thereon, which when executed by the processor cause the system to: illuminate the atom array; detect a series of frames of scattered light from the illuminated atom array during a time t; estimate a flux of an image based on the binary frames detected during time t; perform a binary classification based on a flux of the frames; extract quantum state information from the frames; and estimate each neutral atom qubit state based on the extracted quantum state information.

Abstract: In accordance with the described techniques, a processing device receives a document that includes a table, and uses a machine learning model to detect cells in the table and probabilities assigned to the cells indicating whether respective cells correspond to a row header or a column header of the table. Further, the processing device aligns borders of the cells along horizontal axes of corresponding rows of the table and along vertical axes of corresponding columns of the table. In addition, the processing device generates a table structure based on the aligned cells and the probabilities such that the table structure includes the aligned cells arranged in the rows and columns.

Abstract: The disclosed technology relates to a write driver and a method for operating the write driver for a memory device. The write driver is connected to a memory line of the memory device. Multiple memory cells of the memory device are connected to the memory line at different distances from the write driver. The operating method comprises controlling the write driver to provide a smaller amount of current for accessing a first memory cell of the memory cells, and controlling the write driver to provide a larger amount of current for accessing a second memory cell of the memory cells. Thereby, the first memory cell is connected to the memory line at a smaller distance to the write driver than the second memory cell.

Abstract: Techniques for implementing proactive data security operations for files using an analysis of access permission levels for the files are disclosed. In some embodiments, a computer system performs operations comprising: determining that data of a file includes sensitive information based on an analysis of the data using a data classification model; determining that access to the file is open using an access classification model; and based on the determination that the data of the file includes sensitive information and the determination that the access to the file is open, causing a notification to be displayed on a computing device of a user, the notification comprising an indication that the file includes sensitive information and that access to the file is open.

Abstract: Embodiments disclosed herein may include an apparatus that includes a first substrate, where the first substrate comprises a glass layer, and a second substrate over the first substrate, where the second substrate comprises an organic buildup layer. In an embodiment, a first width of the first substrate is greater than a second width of the second substrate. In an embodiment, an edge between a first corner of the first substrate and a second corner of the first substrate comprises a curve.

Abstract: In accordance with some embodiments, systems, methods, and media for single photon depth imaging with improved efficiency using compressive histograms are provided. In some embodiments, the system comprises: a light source; a detector configured to detect arrival of individual photons; a processor programmed to: detect a photon arrival; determine a time bin i of the photon arrival in a range from 1 to N a total number of time bins; update a compressed histogram comprising K stored values representing bins of the compressed histogram based on K values in a code word represented by an ith column of a coding matrix C having dimension K×N, with each column different than each other column, and each column corresponds to a single time bin i; and estimate a depth value based on the K values.

Abstract: In accordance with some embodiments, systems, methods, and media for generating and using neural networks having improved efficiency for analyzing video are provided. In some embodiments, the method comprises: providing image data to a trained neural network; receiving, at a neuron, a delta-based input ?in from a previous layer; generating an output g(?in) of a linear transform g; generating an updated state variable a based on g(?in) and a current a; generating an output ƒ(a) of an activation function ƒ based on updated a; generating an updated state variable d based on a current d, a state variable b, and ƒ(a); generating an updated b based on output ƒ(a); transmitting d to a next layer based on a transmission policy and subtracting the value from d; and receiving an output from the trained neural network that represents a prediction based on the image data.

Abstract: Techniques are provided for providing a storage abstraction layer for a composite aggregate architecture. A storage abstraction layer is utilized as an indirection layer between a file system and a storage environment. The storage abstraction layer obtains characteristic of a plurality of storage providers that provide access to heterogeneous types of storage of the storage environment (e.g., solid state storage, high availability storage, object storage, hard disk drive storage, etc.). The storage abstraction layer generates storage bins to manage storage of each storage provider. The storage abstraction layer generates a storage aggregate from the heterogeneous types of storage as a single storage container. The storage aggregate is exposed to the file system as the single storage container that abstracts away from the file system the management and physical storage details of data of the storage aggregate.

Abstract: An artificial intelligence-based method for interpreting Piping and Instrumentation Diagram (P&ID) sheets is disclosed. The method includes obtaining a plurality of P&ID sheets in digital format and localizing symbols therein by generating bounding boxes. The localized symbols are labeled as a single generic class to generate a training dataset. A self-supervised learning process trains an artificial intelligence model using the training dataset to identify distinctive symbol features by minimizing the distance between embeddings of similar symbols while maximizing the distance between dissimilar ones. The trained model generates predictive output describing symbols in new P&ID sheets not used in training. The predictive output is then presented for further use.

Abstract: Vehicle dealership computing systems and related apparatuses, methods, and computer-readable instructions are disclosed. A sales agent graphical user interface (GUI) includes input elements configured to receive vehicle sale information for a proposed vehicle sale of a uniquely identified vehicle. The sales agent graphical user interface also displays a deal quality score for the proposed vehicle sale generated based, at least in part, on the vehicle sale information and multifactor estimates of costs incurred by a vehicle dealership for the uniquely identified vehicle. The sales agent GUI further displays an approval decision indicating whether the vehicle sale is approved by the vehicle dealership based, at least in part, on the deal quality score and one or more deal quality score threshold values.

Abstract: A method includes projecting a first illumination pattern towards a scene. The first illumination pattern illuminates a first subset of a field of view. The method includes capturing a first measurement corresponding to light reflected from the scene in response to the first illumination pattern. The method includes projecting a second illumination pattern toward the scene. The second illumination pattern illuminates the second subset of the field of view. The method includes capturing a second measurement corresponding to light reflected from the scene in response to the second illumination pattern. The method includes comparing the first measurement with the second measurement and determining a depth value for an object within the scene based on comparing the first measurement with the second measurement. The method includes controlling movement of a vehicle based on the depth value for the object.

Abstract: Embodiments are disclosed for a process of detecting and processing curved text in a document using a digital design system. The method may include identifying, by a page segmentation model, a plurality of paragraph objects in a document. The disclosed systems and methods further comprise determining that a paragraph object of the plurality of paragraph objects includes curved text in view of positions of baselines of text runs in the paragraph object. The processing of the curved text in the paragraph object can include determining spacing data for text runs of the curved text in the paragraph object. The disclosed systems and methods further comprise presenting output data representing the curved text using the spacing data for the text runs of the curved text.

Abstract: Methods and systems for processing frame data are disclosed. The methods and systems include: obtaining a sequence of data, the sequence comprising at least a first frame; applying the sequence of data to a machine learning model; and providing an inference result based on the machine learning output score from the machine learning model. The machine learning model is configured to: determine at least one token-level error based on a difference between at least one token of a first representation corresponding to the first frame and a second representation; perform a first transformer operation based on the token subset to produce an output representation corresponding to the token subset; scatter the output representation to a buffer representation corresponding to the first representation; and produce a machine learning output score based on the buffer representation. Other aspects, embodiments, and features are also claimed and described.