Abstract: The present application discloses a server system, a job execution method and apparatus, a device, and a medium. The server system includes a server and an extended computing domain; the server includes a processor control domain and a local computing domain, the local computing domain includes a plurality of local computing units, the processor control domain is connected to the local computing units, and the local computing units are configured to execute local computing tasks; the extended computing domain includes an extended controller and a plurality of extended computing units connected to the extended controller, the server is connected to the extended controller through an extended cable compliant with a peripheral component interconnect express protocol and/or an external communication interface, the extended controller is configured to communicate with the server to acquire extended computing tasks, and the extended computing units are configured to execute the extended computing tasks.

Abstract: Original data related to a question-answer task is obtained. Based on the original data, at least an initial corpus is determined by using a first model, the initial corpus includes a standard question and an answer to the standard question. By using the first model, at least a similar question is determined based on the standard question, a text similarity between the similar question and the standard question satisfies a similarity condition. A corpus database is generated based on at least the initial corpus and the similar question, the corpus database includes at least a corpus including the standard question, the answer to the standard question, and at least the similar question. A second model for performing the question-answer task is trained by using at least the corpus as a training sample. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

Abstract: Methods and systems for object detection are disclosed. The methods and systems include: receiving a video frame, determining an execution configuration among multiple configurations at an inference time based on the video frame and multiple metrics (e.g., a latency metric, an accuracy metric, and an energy metric), and performing object detection or object tracking at the inference time based on the video frame and the execution configuration. Other aspects, embodiments, and features are also claimed and described.

Abstract: A data storage method includes receiving pieces of data, where each piece of data includes tag values. The tags include a first tag and a second tag that are specified as a sort key, and the first tag ranks before the second tag in the sort key. The method determines a tag value set to which a tag value of the first tag in each piece of data belongs, and determines a storage sequence of the pieces of data based on a sequence in the sort key, identification information of the tag value set to which the tag value of the first tag in each piece of data belongs, and a tag value of the second tag in each piece of data. The pieces of data are stored based on the storage sequence of the pieces of data.

Abstract: A data query method includes: providing a data query interface; obtaining an aggregation query task from the data query interface, where the aggregation query task is used to query for a total amount of data that meets a query condition; and displaying, in the data query interface, a first estimated query result of the aggregation query task, where the first estimated query result includes a first total amount of data that meets the query condition and that is obtained through approximate estimation based on a first partial exact query result.

Abstract: The present disclosure provides an oral cone beam X-ray imaging system and its fast positioning method. The working modes of the imaging system includes an oral CT shooting mode, an oral panoramic shooting mode, and a head frontal and lateral shooting mode. The system includes a source, a flat panel detector, a rotating driving device, a data processing device, and a control device. The number of sources, flat panel detectors, and rotating driving devices is one to form a single-path imaging system. The working mode also includes a fast positioning mode to perform Self-Adaptation positioning of the imaging system based on the positioning result of the fast positioning mode. In the rapid positioning method, low-dose X-rays are emitted; CT images are received and reconstructed to obtain the current pose of the measured object; and based on the current pose, the imaging system performs Self-Adaptation positioning to perform imaging in the oral panoramic shooting mode or the head lateral shooting mode.

Abstract: A biometric input system for an electronic device is provided. The biometric input system may be a fingerprint sensing system. The biometric input system includes a biometric sensing component, which may be a capacitive sensing component. The biometric input system also includes a composite cover element, which may be a dielectric cap or coating, and the biometric sensing component is capable of receiving a biometric input from a user through the composite cover element. Electronic devices including the biometric input system are also provided.

Abstract: Methods, systems, apparatuses, devices, and computer program products are described. A flow generation service may receive a natural language input that indicates instructions for automating a task according to a first process flow. Using a large language model (LLM), the flow generation service may decompose the natural language input into a set of elements (e.g., logical actions) and connectors, where the LLM may be trained on first metadata corresponding to a second process flow that is created manually by a user. In addition, using the LLM, the flow generation service may generate second metadata corresponding to each of the set of elements based on decomposing the natural language input. The flow generation service may sequence and merge the set of elements to generate the first process flow. In some examples, the flow generation service may send, for display to a user interface of a user device, the first process flow.

Abstract: The present application relates to the field of communications, and provides a high-speed communication method and apparatus of a heterogeneous device and a heterogeneous communication system. The method comprises: a high-speed interconnection remote virtualization processor receives a high-speed interconnection operation; the high-speed interconnection remote virtualization processor converts the high-speed interconnection operation to a register operation and a memory data migration operation on a heterogeneous accelerator of a target heterogeneous device; the high-speed interconnection remote virtualization processor converts the register operation and the memory data migration operation to a communication request; and the high-speed interconnection remote virtualization processor communicates with the target heterogeneous device by means of the communication request, so as to execute the register operation and the memory data migration operation.

Abstract: According to embodiments of the present invention, there is provided a sensor including: a primary sensing part including a first electrode and a second electrode electrically coupled to the first electrode; a secondary sensing part including a third electrode and a fourth electrode electrically coupled to the third electrode; and electrical measurement unit(s). The first, second, third, and fourth electrodes respectively include a first material, a second material, a third material, and a fourth material. The first and/or second electrodes and third and/or fourth electrodes may be arranged to move relatively to each other to generate electrical signal(s) representative of quantifiable parameter(s) of relative motion. According to further embodiments, a method for determining quantifiable parameter(s) of relative motion between a movable object and a stationary (or another movable) object is also provided.

Abstract: A training framework includes a transparent and unbiased dataset generation pipeline to generate unbiased multi-modal training data for training a multi-modal LLM. Specifically, one or more images may be annotated using image recognition models, e.g., for object detection, attributes, relations, segmentation, etc. Then, the generated annotations are used to generate scene graph. A scene graph is a data structure that represents objects with attributes in an image as nodes and relationships between objects in an image as edges. Several computer programs are then used to systematically generate question-answer pairs. Because the computer programs include a set of known rules, how the data is generated is known explicitly and thus transparent. The question-answer pairs may be of several types, e.g., a type associated with each of the types of image recognition models. The question-answer pairs may be included in a training dataset and used to train a multimodal LLM.

Abstract: The present application discloses a server system, a job execution method and apparatus, a device, and a medium. The server system includes a server and an extended computing domain; the server includes a processor control domain and a local computing domain, the local computing domain includes a plurality of local computing units, the processor control domain is connected to the local computing units and the local computing units are configured to execute local computing tasks; the extended computing domain includes an extended controller and a plurality of extended computing units connected to the extended controller, the server is connected to the extended controller through an extended cable compliant with a peripheral component interconnect express protocol and/or an external communication interface, the extended controller is configured to communicate with the server to acquire extended computing tasks, and the extended computing units are configured to execute the extended computing tasks.

Abstract: Embodiments described herein provide a mechanism for replacing existing text encoders in text-to-image generation models with more powerful pre-trained language models. Specifically, a translation network is trained to map features from the pre-trained language model output into the space of the target text encoder. The training preserves the rich structure of the pre-trained language model while allowing it to operate within the text-to-image generation model. The resulting modularized text-to-image model receives prompt and generates an image representing the features contained in the prompt.

Abstract: Embodiments described herein provide a vision-language neural network framework that outputs a text response to a user text query relating to the media content of the video input. Specifically, the vision-language neural network may comprise (1) a vision encoder (ViT) transforming each frame input from the video input into a set of tokens, (2) a frame-level tokenizer to reduce the number of tokens, (3) a temporal encoder to build video-level token representations, and (4) an autoregressive LLM generating a text output based on such video tokens and text prompt tokens.

Abstract: A system may receive video information. The system may extract light weight features from the video information. The system may select a combination of light-weight features and heavy weight feature types, where the light-weight features are extracted from the video information. The system may forecast, based on a combination of the light-weight features and the heavy weight feature types, accuracy and latency metrics for performing the object detection and tracking using a plurality of candidate branch configurations, respectively. The system may select a branch configuration from the plurality of candidate branch configurations in response to satisfaction of an optimization criterion. The system may perform object detection and tracking based on the selected branch configuration. Performing object detection and tracking may include extracting heavy weight features according to the branch configuration.

Abstract: Embodiments described herein provide a method of performing a vision-language task by a neural network multimodal model in response to multiple input images, the method comprising: receiving, via a data interface, a text input and an image input; generating text tokens based on the text input; generating a plurality of image patches, wherein each image patch of the plurality of image patches includes a portion of the image input at substantially a same resolution as the image input; generating a downsized image based on a downsizing of the image input; generating vision tokens based on the plurality of image patches and the downsized image; generating, via a neural network based language model, an output based on the text tokens and the vision tokens; and updating parameters of the neural network based language model based on a loss objective based on the output.

Abstract: Provided is a system that includes at least one processor programmed or configured to receive an XML data file, wherein the XML data file includes data associated with one or more input parameters of a machine learning model, generate a code generation template based on the data associated with one or more input parameters of the machine learning model included in the XML file, where the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate for an account of a user, and generate a file of executable code based on the code generation template, wherein the file of executable code includes instructions that, when executed by at least one processor, causes at least one processor to retrieve transaction aggregate data associated with the transaction aggregate for the account of the user. A method and computer program product are also provided.

Abstract: Embodiments described herein provide a generation model comprising a video-specific variational auto-encoder (VAE) for effective compression of video pixel information with reduced spatial and temporal dimensions and a video diffusion transformer (vDiT) to generate latent representations of frames. Specifically, the VAE may, instead of encoding each frame independently, incorporate both temporal and spatial compression. This significantly decreases the token length, improves the computational cost of training and inference, and facilitates the generation of long videos. The encoded training video, in the form of latent representations from a VAE encoder may then be passed to the vDiT to reconstruct the latent representations during training. The trained vDiT may then generate latent representations of a video in response to a text input, and the latent representations may be converted to a video output by a VAE decoder.

Abstract: Embodiments described a field extraction system that does not require field-level annotations for training. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

Abstract: Embodiments described herein provide a method of image generation. The method includes a fixed diffusion model, and a trainable diffusion model. The fixed diffusion model may be pretrained on a large training corpus. The trainable diffusion model may be used to control the image generation of the fixed diffusion model by modifying internal representations of the fixed diffusion model. A task instruction may be provided in addition to a text prompt, and the task instruction may guide the trainable diffusion model together with the visual conditions. The visual conditions may be adapted according to the task instruction. During training, a fixed number of task instructions may be used. At inference, unseen task instructions may be used by combining convolutional kernels of the visual condition adapter.