Abstract: A method for generating content using a diffusion model of an electronic device, may include: obtaining latent vectors of an input content; inputting the latent vectors into a first lightweight adapter configured for the first application type from among a plurality of lightweight adapters configured individually for application types of the plurality of applications; transforming the latent vectors of the input content into a plurality of intermediate latent vectors using the first lightweight adapter; performing a denoising operation to transform the plurality of intermediate latent vectors into a plurality of next operation vectors; and generating the final content belonging to the application type by decoding the next operation vectors; and outputting the final content.

Abstract: A method for validating a trained artificial intelligence (AI) model on a device is provided. The method includes deploying a validation model generated by applying a plurality of anticipated configurational changes associated with the trained AI model requiring validation. Further, the method includes providing input data to each of the validation model and the trained AI model for receiving an output from each of the validation model and the trained AI model, wherein the output of the validation model is further based on one or more actual configurational deviations that occurred during training of the trained AI model since deployment of the trained AI model on the device. Furthermore, the method includes combining the output of each of the validation model and the trained AI model to validate the trained AI model.

Abstract: A method for processing an input frame for an on-device AI model is provided. The method may include obtaining an input frame. The method may include building at least one kernel independent of the scale of the input frame by passing input variables to the at least one kernel using preprocessor directives independent of the scale of the input frame. The method may include inputting the input frame to the on-device AI model including the at least one kernel independent of the scale of the input frame. The method may include processing the input frame in the on-device AI model.

Abstract: Embodiments herein provide a method and system for network and hardware aware computing layout selection for efficient Deep Neural Network (DNN) Inference. The method comprises: receiving, by the electronic device, a DNN model to be executed, wherein the DNN model is associated with a task; dividing the DNN model into a plurality of sub-graphs, wherein each sub-graph is to be processed individually; identifying a computing unit from a plurality of computing units for execution of each sub-graph based on a complexity score; and determining a computing layout from a plurality of computing layouts for each identified computing unit, wherein the sub-graph is executed on the identified computing unit through the determined computing layout.

Abstract: Disclosed herein is a method and an optimization unit for optimizing and/or improving efficiency of resource utilization in an embedded computing system executing Artificial Intelligence (AI) applications. The method includes: detecting, by an optimization unit comprising processing circuitry and/or executable program instructions configured in the embedded computing system, a launch of an AI application on the embedded computing system; retrieving a runtime profile corresponding to the AI application, the runtime profile indicating resource requirements for executing the AI application; and configuring a runtime environment of the embedded computing system for the AI application based on the runtime profile corresponding to the AI application.

Abstract: A method for compensating for gyroscope drift on an electronic device includes receiving by a data processing unit, measurement data from a gyroscope. The method includes computing, by the data processing unit, a compensation parameter by analyzing the measurement data received from the gyroscope with respect to variations in temperature of the gyroscope. The method includes compensating, by the data processing unit, the measurement data by correcting the measurement data with the computed compensation parameter. The compensation parameter is continuously validated to correct the measurement data with the compensation parameter. Further, the received measurement data is updated continuously based on the computed compensation parameter, independent of the gyroscope on the electronic device, thereby facilitating adaptive drift compensation.

Abstract: A method for compensating for gyroscope drift on an electronic device includes receiving by a data processing unit, measurement data from a gyroscope. The method includes computing, by the data processing unit, a compensation parameter by analyzing the measurement data received from the gyroscope with respect to variations in temperature of the gyroscope. The method includes compensating, by the data processing unit, the measurement data by correcting the measurement data with the computed compensation parameter. The compensation parameter is continuously validated to correct the measurement data with the compensation parameter. Further, the received measurement data is updated continuously based on the computed compensation parameter, independent of the gyroscope on the electronic device, thereby facilitating adaptive drift compensation.