Abstract: A communication system includes a network device and a communication device. The communication device can communicate with the network device. The communication device includes a transmitter module and a control circuit. The control circuit can control the transmitter module to selectively transmit an RF (Radio Frequency) signal to the network device.

Abstract: Methods, systems, and computer programs encoded on a computer storage medium, that relate to generating quantization tables that are used during digital image compression of a digital image. Multiple training images are obtained. A model can be trained using the training images to generate a quantization table that can be used during encoding of an input image. For each training image, a quantization table can be obtained using the model. Using the quantization table, an encoded digital image is obtained for the training image. Using the encoded digital image and the training image, an image quality loss and a compression loss can be determined. An overall loss of the model can be determined by combining the image quality loss and the compression loss for the training image. The model can be updated based on the overall loss.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a generative neural network that has parameters. In one aspect, one of the methods include: obtaining a context input; processing, by the generative neural network, the context input to generate a plurality of training outputs; for each objective in a set of objectives and for each of the plurality of training outputs: determining a respective quality score of the training output relative to each other training input in the plurality of training outputs with respect to the objective; and determining a calibrated reward for the training output with respect to the objective based on the respective quality scores of the training output with respect to the objective; selecting a positive training output and a negative training output; and training the generative neural network on the positive training output and the negative training output.

Abstract: A system and a method may include a speech recognition device configured to acquire user speech information, convert the acquired user speech information into user demand information in a text form, classify the converted user demand information, determine whether a type of the user demand information is a customized scenario, and, if the type of the user demand information is determined to be the customized scenario, generate user demand information of the customized scenario. The system may further include a service-oriented architecture (SOA) atomic function library configured to provide status information of a sensor and an actuator of the vehicle. The system may further include a control device configured to analyze the user demand information based on large language models (LLMs) and generate a plan for a customized scenario suitable for a user demand by using user demand information of the customized scenario and the SOA atomic function library.

Abstract: An information processing method, applied to an information processing system, where the information processing system includes a terminal device, an information management device, communication service systems, and a gateway device connected to the information management device and to each of the communication service systems, each communication service system corresponding to a respective communication service network, includes detecting, by the gateway device, a network connection status of the terminal device through each of the communication service systems, receiving, by the gateway device, detection response information from the terminal device through a target communication service network of the communication service networks, and determining, by the gateway device, target routing information that indicates that the gateway device and the terminal device are connected through the target communication service network.

Abstract: The present disclosure provides a student performance evaluation method and system based on artificial intelligence (AI) identification data, and relates to the field of intelligent education. A lightweight network model suitable for student performance evaluation takes the AI identification data as an input and evaluation results as an output. A training data generation algorithm is provided, and multidimensional AI identification data and labels are uniformly processed into training data suitable for the network model through the above algorithm, which can solve the problems that dimensions between any AI identification data and various labels are not uniform, and original data cannot meet training of a multidimensional and cross-time prediction model. A simulated data generation algorithm and a simulated label generation algorithm are provided, and simulated training data is generated using these algorithms in conjunction with the training data generation algorithm.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for training a target generative neural network over a plurality of training iterations. At each iteration, a first data item is generated by processing a conditioning input using the target generative neural network. An improvement generative neural network then processes the first data item and the conditioning input to generate a second, preferred data item. A training example is generated that includes the first and second data items and indicates that the second data item is preferred over the first. The target generative neural network is then trained on this training example. By using this iterative process to dynamically generate preference data, the described techniques improve the performance of the generative neural network beyond the limitations of static, offline datasets without requiring computationally expensive reward models or external human annotation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a diffusion neural network using a region-aware fine-tuning process. After training, the diffusion neural network can be used to generate an image conditioned on a conditioning input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting and decoding a visually imperceptible or perceptible watermark. A watermark detection apparatus determines whether the particular image includes a visually imperceptible or perceptible watermark using detector a machine learning model. If the watermark detection apparatus detects a watermark, the particular image is routed to a watermark decoder. If the watermark detection apparatus cannot detect a watermark in the particular image, the particular image is filtered from further processing. The watermark decoder decodes the visually imperceptible or perceptible watermark detected in the particular image. After decoding, an item depicted in the particular image is validated based data extracted from the decoded visually imperceptible or perceptible watermark.

Abstract: Provided is an efficient and scalable attention model that can be referred to as multi-axis attention. Example implementations can include two aspects: blocked local and dilated global attention. These design choices allow global-local spatial interactions on arbitrary input resolutions with only linear complexity. The present disclosure also presents a new architectural element by effectively blending the proposed multi-axis attention model with convolutions. In addition, the present disclosure proposes a simple hierarchical vision backbone, example implementations of which can be referred to as MaxViT, by simply repeating the basic building block over multiple stages. Notably, MaxViT is able to “see” globally throughout the entire network, even in earlier, high-resolution stages.

Abstract: Aspects of the disclosure are directed to text to image generative models fine-tuned to generate images that account for performance in addition to quality. For example, in a digital content domain, the generated images can be not only visually appealing but perform well as advertising assets, e.g., result in improved click through rate and/or conversion rate. Accounting for performance and quality can reduce processing cost and memory usage when generating images from text prompts, as the resolution of the image can be balanced with its function, allowing for reduced quality images that can still perform well.

Abstract: The present invention belongs to the technical field of surface treatment for metal materials, and particularly relates to an environment-friendly water-based treatment agent for improving the phosphatability of high-strength steel. The water-based treatment agent is prepared by dissolving or dispersing a composition in an aqueous medium. The water-based treatment agent specifically consists of: A. a fluoride ion-containing compound; B. a compound selected from metal ion compounds containing Cu, Zn, Mn, Ni or Fe; C. a compound selected from organic acids; and D. a compound selected from surfactant. The water-based treatment agent can be diluted in water at a ratio of 1:0-20 for subsequent use. The treatment agent can enable the surface of a high-strength steel plate to have excellent phosphatability and is mainly applied to high-strength steel surface modification treatment.

Abstract: Example aspects of the present disclosure are directed to systems and methods which feature a machine-learned video super-resolution (VSR) model which has been trained using a bi-directional training approach. In particular, the present disclosure provides a compression-informed (e.g., compression-aware) super-resolution model that can perform well on real-world videos with different levels of compression. Specifically, example models described herein can include three modules to robustly restore the missing information caused by video compression. First, a bi-directional recurrent module can be used to reduce the accumulated warping error from the random locations of the intra-frame from compressed video frames. Second, a detail-aware flow estimation module can be added to enable recovery of high resolution (HR) flow from compressed low resolution (LR) frames. Finally, a Laplacian enhancement module can add high-frequency information to the warped HR frames washed out by video encoding.

Abstract: Systems and methods of the present disclosure are directed to a computing system. The computing system can obtain a message vector and video data comprising a plurality of video frames. The computing system can process the input video with a transformation portion of a machine-learned watermark encoding model to obtain a three-dimensional feature encoding of the input video. The computing system can process the three-dimensional feature encoding of the input video and the message vector with an embedding portion of the machine-learned watermark encoding model to obtain spatial-temporal watermark encoding data descriptive of the message vector. The computing system can generate encoded video data comprising a plurality of encoded video frames, wherein at least one of the plurality of encoded video frames includes the spatial-temporal watermark encoding data.

Abstract: Systems and methods are directed to a computing system. The computing system can include one or more processors, a message embedding model, a message extraction model, and a first set of instructions that cause the computing system to perform operations including obtaining the three-dimensional image data and the message vector. The operations can include inputting three-dimensional image data and a message vector into the message embedding model to obtain encoded three-dimensional image data. The operations can include using the message extraction model to extract an embedded message from the encoded three-dimensional image data to obtain a reconstructed message vector. The operations can include evaluating a loss function for a difference between the reconstructed message vector and the message vector and modifying values for parameters of at least the message embedding model based on the loss function.

Abstract: The present disclosure provide a method for detecting traffic accidents by using the helmet of an electric bicycle, and the method includes: acquiring real-time state information of the electric bicycle; controlling a camera mounted on a front of the helmet of the electric bicycle to enter a snapshot mode and acquiring environment image information captured by the camera according to a first preset time interval in response that the electric bicycle is in the started state; and in response that the environment image information comprises the preset traffic accident image, controlling the camera to enter a first video recording mode, and sending the environment image information of a first preset period of time recorded by the camera and/or a first warning command to a first target object after waiting for the first preset period of time.

Abstract: Provided are a genomic prediction method and apparatus based on a genotype-environment interaction heterogeneous graph, relating to the technical field of bioinformatics.

Abstract: An electronic device and a state switching method are provided in the present disclosure. The electronic device includes a first main body, a second main body, and a rotating-axle apparatus, where the rotating-axle apparatus connects the first main body with the second main body to make the second main body at an open state or a closed state relative to the first main body; and an air outlet is disposed on a side of the first main body. The rotating-axle apparatus is configured to, in a process of rotating the second main body around a rotation center to the open state, drive the second main body to ascend along a first direction relative to the first main body and move above the first main body to expose the air outlet.

Abstract: Lighting module for a motor vehicle comprising a matrix light source grouping together a plurality of elementary light sources, and a control module for a motor vehicle. Method for controlling the matrix source of said module, noteworthy in that it allows a default lighting setpoint to be generated.

Abstract: The technology provides for enhanced image cropping via in-context learning. It includes an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. It also includes an iterative refinement strategy to iteratively enhance the predicted crops. The image cropping framework is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. The approach employs a trained large vision-language model associated with in-context learning. For instance, given an input image (whether from free-form, subject-aware or aspect ratio-aware cropping), the top-K semantically similar images from a dataset are retrieved as an in-context learning prompt. Then the in-context learning prompt is fed to a pretrained vision-language model to generate a set of crops. The crop candidates of the set are iteratively refined to yield a final output crop.