Abstract: Systems and method directed to assistive document generation are described. More specifically, similar documents share large portions of reusable text structures that can be used to generate an initial document thereby saving a user time. To generate the document, an indication to create the document may be received and based on the indication, a plurality of example documents and grounding content may be identified. Example documents may be existing documents that are similar to a target document of the writer. Grounding information may refer to content that is relevant, timely, and accurate when applied to the target document. The plurality of example documents and the grounding content may be received, and a document sketch based on the example documents and the grounding content may be generated and contains a plurality of predicted text sequences based on the example documents and the grounding content.

Abstract: Facilitating real-time power optimization in advanced networks (e.g., 5G, 6G, and beyond) is provided herein. Operations of a method can include determining, by a system comprising a memory and a processor, a power distribution setting for a user equipment that includes multiple radios based on a historical radio power usage, a historical performance result, a current location, and an application currently executing on the user equipment. The method also can include implementing, by the system, the power distribution setting across the multiple radios of the user equipment. The first radio of the multiple radios can be a first radio type and a second radio of the multiple radios can be a second radio type, different from the first radio type.

Abstract: Techniques are provided for determining consistency measures for image segmentation. For instance, a system can determine a first segmentation feature associated with a first segmentation mask of a first image frame. The system can determine a second segmentation feature associated with a second segmentation mask of a second image frame. The second segmentation feature corresponds to the first segmentation feature. The system can determine a first image feature of the first image frame that corresponds to the first segmentation feature and a second image feature of the second image frame that corresponds to the second segmentation feature. The system can determine a first similarity measurement between the first image feature and the second image feature. The system can further determine a temporal consistency measurement associated with the first image frame and the second image frame based at least in part on the first similarity measurement.

Abstract: A method for processing a video includes receiving a video as an input at a first layer of an artificial neural network (ANN). A first frame of the video is processed to generate a first label. Thereafter, the artificial neural network is updated based on the first label. The updating is performed while concurrently processing a second frame of the video. In doing so, the temporal inconsistency between labels is reduced.

Abstract: A processor-implemented method for image compression using an artificial neural network (ANN) includes receiving, at an encoder of the ANN, an image and a spatial segmentation map corresponding to the image. The spatial segmentation map indicates one or more regions of interest. The encoder compresses the image according to a controllable spatial bit allocation. The controllable spatial bit allocation is based on a learned quantization bin size.

Abstract: A processing system including at least one processor of a base station of a cellular network may receive first uplink transmissions from a user equipment via multiple carriers in accordance with a carrier aggregation technique and may detect, for the first uplink transmissions, at least one of: a first signal to noise ratio for the user equipment exceeding a first signal to noise threshold or a first uplink throughput for the user equipment exceeding a first uplink throughput threshold. The processing system may next transmit a first instruction to the user equipment to switch from the carrier aggregation technique to a first uplink multiple input multiple output technique, in response to the detecting. The processing system may then receive second uplink transmissions from the user equipment in accordance with the first uplink multiple input multiple output technique.

Abstract: Systems, methods, and non-transitory media are provided for providing spatiotemporal recycling networks (e.g., for video segmentation). For example, a method can include obtaining video data including a current frame and one or more reference frames. The method can include determining, based on a comparison of the current frame and the one or more reference frames, a difference between the current frame and the one or more reference frames. Based on the difference being below a threshold, the method can include performing semantic segmentation of the current frame using a first neural network. The semantic segmentation can be performed based on higher-spatial resolution features extracted from the current frame by the first neural network and lower-resolution features extracted from the one or more reference frames by a second neural network. The first neural network has a smaller structure and/or a lower processing cost than the second neural network.

Abstract: Aspects of the subject disclosure may include, for example, obtaining a reference signal, power information regarding the reference signal, and maximum power threshold for the communication device from a base station over a communication network. Further embodiments can include measuring a power of reference signal obtained from the base station resulting in a measure power, and determining a path loss between the base station and the communication device based on the measured power. Additional embodiments can include adjusting the antenna array to generate a coarse power adjustment for the communication device based on the path loss and the maximum power threshold, and providing a transmission signal to the base station according to the coarse power adjustment over the communication network. Other embodiments are disclosed.

Abstract: Automated orienting of customer premises equipment (CPE) is disclosed. An orientation of a CPE can be automatically adapted based on a model of an environment of the CPE, an environmental condition, etc. Adapting an orientation can change roll, pitch, yaw, and skew of a whole CPE, and/or a portion of the CPE. In embodiments, a CPE can perform exploratory orienting to update a mapping of the environment of the CPE. This can enable the CPE to rank, sort, order, etc., alternate orientations to satisfy one or more rules related to operation of the CPE. This can facilitate the CPE mitigating a hazard condition, altering a performance metric, accommodating a customer preference, etc. In embodiments, a learning component can be employed to predict a preferred adjustment to an orientation based on user input, a rule, historical condition information, contemporaneous condition information, etc.

Abstract: A method of image compression includes receiving an image. Multiple quantized latent representations are generated to represent features of the image. Each of the quantized latent representations has a different resolution and is generated at staggered timings. Each of the later generated quantized latent representations is conditioned on each of the prior generated quantized latent representations. The multiple quantized latent representations are decoded to reconstruct the image.

Abstract: Aspects of the subject disclosure may include, for example, obtaining a reference signal, power information regarding the reference signal, and maximum power threshold for the communication device from a base station over a communication network. Further embodiments can include measuring a power of reference signal obtained from the base station resulting in a measure power, and determining a path loss between the base station and the communication device based on the measured power. Additional embodiments can include adjusting the antenna array to generate a coarse power adjustment for the communication device based on the path loss and the maximum power threshold, and providing a transmission signal to the base station according to the coarse power adjustment over the communication network. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, obtaining a reference signal, power information regarding the reference signal, and maximum power threshold for the communication device from a base station over a communication network. Further embodiments can include measuring a power of reference signal obtained from the base station resulting in a measure power, and determining a path loss between the base station and the communication device based on the measured power. Additional embodiments can include adjusting the antenna array to generate a coarse power adjustment for the communication device based on the path loss and the maximum power threshold, and providing a transmission signal to the base station according to the coarse power adjustment over the communication network. Other embodiments are disclosed.

Abstract: A method includes determining a quality of service class identifier (QCI) level for an application running on a user device, selecting a connected mode discontinuous reception (CDRX) profile based on the QCI level, and transmitting the CDRX profile to the user device to be used when running the application. The QCI level may be indicative of delay sensitivity of the application and the CDRX profile may be selected based on the delay sensitivity of the application.

Abstract: A processor-implemented method for image compression using an artificial neural network (ANN) includes receiving, at an encoder of the ANN, an image and a spatial segmentation map corresponding to the image. The spatial segmentation map indicates one or more regions of interest. The encoder compresses the image according to a controllable spatial bit allocation. The controllable spatial bit allocation is based on a learned quantization bin size.

Abstract: Aspects of the subject disclosure may include, for example, identifying, by a processing system including a processor, a penetration loss, resulting in an identified penetration loss, obtaining, by the processing system, an indication of a first frequency or a first frequency range associated with a first communication, and identifying, based on the identified penetration loss and the indication, a type of cover that at least partially encases the processing system, resulting in an identified type of cover. Other embodiments are disclosed.

Abstract: A method includes determining a quality of service class identifier (QCI) level for an application running on a user device, selecting a connected mode discontinuous reception (CDRX) profile based on the QCI level, and transmitting the CDRX profile to the user device to be used when running the application. The QCI level may be indicative of delay sensitivity of the application and the CDRX profile may be selected based on the delay sensitivity of the application.

Abstract: Certain aspects of the present disclosure provide techniques for training neural networks using hierarchical supervision. An example method generally includes training a neural network with a plurality of stages using a training data set and an initial number of classification clusters into which data in the training data set can be classified. A cluster-validation set performance metric is generated for each stage based on a reduced number of classification clusters relative to the initial number of classification clusters and a validation data set. A number of classification clusters to implement at each stage is selected based on the cluster-validation set performance metric and an angle selected relative to the cluster-validation set performance metric for a last stage of the neural network. The neural network is retrained based on the training data set and the selected number of classification clusters for each stage, and the trained neural network is deployed.

Abstract: Certain aspects of the present disclosure provide techniques for cross-task distillation. A depth map is generated by processing an input image using a first machine learning model, and a segmentation map is generated by processing the depth map using a second machine learning model. A segmentation loss is computed based on the segmentation map and a ground-truth segmentation map, and the first machine learning model is refined based on the segmentation loss.

Abstract: Facilitating real-time power optimization in advanced networks (e.g., 5G, 6G, and beyond) is provided herein. Operations of a method can include determining, by a system comprising a memory and a processor, a power distribution setting for a user equipment that includes multiple radios based on a historical radio power usage, a historical performance result, a current location, and an application currently executing on the user equipment. The method also can include implementing, by the system, the power distribution setting across the multiple radios of the user equipment. The first radio of the multiple radios can be a first radio type and a second radio of the multiple radios can be a second radio type, different from the first radio type.

Abstract: Aspects of the present disclosure relate to techniques for interactive content generation. In examples, processed content may be produced by a generative model based on a content seed, such as a sentence or paragraph. User input associated with the processed content may be received, for example to revise the processed content or provide additional input with respect to a subpart of the processed content that is associated with a low confidence score. A generative model may produce updated processed content based at least in part on the previously processed content, the user input, and/or, in some examples, additional content, as may be indicated by a user. Thus, a user may iterate on processed content that is produced by such generative models through successive interactions, thereby enabling the user to provide input to the generative model as part of the content generation process.