Abstract: Techniques and systems for training and/or implementing a text-to-image generation model are provided. A pre-trained multimodal model is leveraged for avoiding slower and more labor-intensive methodologies for training a text-to-image generation model. Accordingly, images without associated text (i.e., bare images) are provided to the pre-trained multimodal model so that it can produce generated text-image pairs. The generated text-image pairs are provided to the text-to-image generation model for training and/or implementing the text-to-image generation model.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback.

Abstract: In implementations of systems for detection and interpretation of log anomalies, a computing device implements an anomaly system to receive input data describing a two-dimensional representation of log templates and timestamps. The anomaly system processes the input data using a machine learning model trained on training data to detect anomalies in two-dimensional representations of log templates and timestamps. A log anomaly is detected in the two-dimensional representation using the machine learning model based on processing the input data. The anomaly system generates an indication of an interpretation of the log anomaly for display in a user interface based on a log template included in the two-dimensional representation.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for building time-decayed line graphs from temporal graph networks for efficiently and accurately generating time-aware recommendations. For example, the time-decayed line graph system creates a line graph of the temporal graph network by deriving interaction nodes from temporal edges (e.g., timed interactions) and connecting interactions that share an endpoint node. Then, the time-decayed line graph system determines the edge weights in the line graph based on differences in time between interactions, with interactions that occur closer together in time being connected with higher weights. Notably, by using this method, the derived time-decayed line graph directly represents topological proximity and temporal proximity. Upon generating the time-decayed line graphs, the system performs downstream predictive modeling such as predicted edge classifications and/or temporal link predictions.

Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for resource provisioning of microservices using guided order of learning in a reinforcement learning framework. In embodiments, service resource information relating to microservices operating in a computing environment is received and used to perform a similarity analysis to generate similarity scores for each of the services. The service resource information is ordered based on a closeness between the similarity scores of the services. The ordered service resource information is inputted into a reinforcement learning agent to generate a resource configuration determination of at least one service of the services. The resource configuration determination is then provided to a provisioning component associated with the computing environment for provisioning the microservice.

Abstract: Some techniques described herein relate to utilizing a machine-learning (ML) model to select respective samples for queries of a query sequence. In one example, a method includes receiving a query in a query sequence, where the query is directed toward a dataset. Samples are available as down-sampled versions of the dataset. The method further include applying an agent to select, for the query, a sample from among the samples of the dataset. The agent includes an ML model trained, such as via intent-based reinforcement learning, to select respective samples for queries. The query is then executed against the sample to output a response.

Abstract: Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

Abstract: Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

Abstract: Techniques for predicting and recommending item bundles in a multi-round conversation to discover a target item bundle that would be accepted by a client. An example method includes receiving an input response in reply to a first item bundle that includes one or more items. A state model is updated to reflect the input response to the first item bundle. A machine-learning (ML) conversation module is applied to the state model to determine an action type as a follow-up to the input response to the first item bundle. Based on selection of a recommendation action as the action type, an ML bundling module is applied to the state model to generate a second item bundle different than the first item bundle. The second item bundle is then recommended.

Abstract: A coupled steering tilting and embedded independent shock absorption swing arm system (STS) system of a personal mobility vehicle, for example, but not limited to, a three-wheeled trike configuration, is disclosed.

Abstract: Tabular data machine-learning model techniques and systems are described. In one example, common-sense knowledge is infused into training data through use of a knowledge graph to provide external knowledge to supplement a tabular data corpus. In another example, a dual-path architecture is employed to configure an adapter module. In an implementation, the adapter module is added as part of a pre-trained machine-learning model for general purpose tabular models. Specifically, dual-path adapters are trained using the knowledge graphs and semantically augmented trained data. A path-wise attention layer is applied to fuse a cross-modality representation of the two paths for a final result.

Abstract: A shell structure of a clothing treating device comprises a rear U-shaped plate, the rear U-shaped plate being bent at two vertical lines to form a left side wall, a right side wall and a rear side wall of a shell, with a cross section being U-shaped. The left side wall and the right side wall are respectively provided with at least one handle part, and the rear U-shaped plate is provided with an air vent communicating with an inside of the shell. As a result, the shell structure of a machine body of the clothing treating device is simplified, the strength is improved, and the assembly efficiency is improved. Also, an air duct arranged in the clothing treating device communicates with the air vent, so that the purpose of exchanging air with the outside through the air vent is realized.

Abstract: Systems and methods that enable the efficient and adaptive allocation of resources dedicated to a virtualized resource-based computation (e.g., one or more information processing tasks) are provided. In one embodiment, a reward model is generated based on a set of statistical distributions, for example, in response to receiving a request to launch a set of VCRs. Thereafter, an expected reward is predicting for each configuration of a set of configurations based on the reward model and one or more parameters of the corresponding configuration. The expected reward indicates an efficiency in distribution or allocation of physical computation resources to the set of VCRs. A configuration of the set of configurations is selected based on the predicted expected reward for the configuration. The set of VCRs are then configured with the selected configuration.

Abstract: Systems and methods for product retrieval are described. One or more aspects of the systems and methods include receiving a query that includes a text description of a product associated with a brand; identifying the product based on the query by comparing the text description to a product embedding of the product, wherein the product embedding is based on a brand embedding of the brand; and displaying product information for the product in response to the query, wherein the product information includes the brand.

Abstract: Some techniques described herein relate to utilizing a machine-learning (ML) model to select respective samples for queries of a query sequence. In one example, a method includes receiving a query in a query sequence, where the query is directed toward a dataset. Samples are available as down-sampled versions of the dataset. The method further include applying an agent to select, for the query, a sample from among the samples of the dataset. The agent includes an ML model trained, such as via intent-based reinforcement learning, to select respective samples for queries. The query is then executed against the sample to output a response.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback.

Abstract: A method for testing terminals includes determining a quantity of terminals to be tested; testing each terminal to be tested in a testing environment and obtaining a quantity of testing results; each testing result includes an actual transmitting power and/or a receiving signal strength; obtaining a first fitting function based on the actual transmitting power, and/or obtaining a second fitting function based on the receiving signal strength; and controlling a target terminal to transmit signals, calculating an actual transmitting power of the target terminal by the first fitting function, and/or controlling the target terminal to receive signals, calculating a receiving signal strength of the target terminal by the second fitting function. A computer apparatus and a non-transitory computer readable medium for testing terminals are also disclosed.

Abstract: The invention provides a method and a system of monitoring a subject. The method comprises the steps of monitoring, from a first angle of detection, a space in which the subject is located to obtain data of the subject from a first perspective view in accordance with the first angle of detection; converting the obtained data of the subject into a three-dimensional data set; processing the three-dimensional data set to create an image of the subject from a second perspective view, said second perspective view being created at a second angle different from the first angle of detection; and analyzing the created image from the second perspective view to determine, calculate, or select one or more characteristics relating to activity of the subject being monitored.

Abstract: Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

Abstract: Techniques of self-checkout alerts based on packaging detection. A given bag type of a bag selected at a self-checkout kiosk is identified out of a bag types available from a bag dispenser associated with the self-checkout kiosk, the bag being an empty bag. A weight range of the empty bag is identified based on the given bag type. An allowed weight range of a combination of the empty bag and a desired item is determined based on the weight range of the empty bag, a weight of the desired item as measured by a terminal scale, and at least one of a measurement tolerance of the terminal scale and a measurement tolerance of a platform scale. A loss prevention alert is generated, and a transaction at the self-checkout kiosk is paused, upon determining that the allowed weight range is exceeded.