Mohamed Bin Zayed University of Artificial Intelligence

A wireless communication network method and system that includes a central server, cellular base stations, edge computing devices, and client devices. The client devices send uplink pilot sequences, which are collected and aggregated by the base stations. The base stations then relay this aggregated pilot data to the central server. The central server deploys network weights for a global deep learning neural network model to the base stations for incorporation into respective local deep learning models, trained to predict optimal beamforming vectors, to the base stations for incorporation into respective local deep learning model. During training the central server integrates adaptive noise into weights received for each of the local deep learning models.

A system and method of training a deep neural network for object detection in an object detection system. The object detection system including a camera and a controller including the DNN. The method including capturing an image by the camera, receiving the image, predicting, using the DNN, a bounding box and corresponding class label, evaluating the prediction with a total loss function including an object detection loss function, a box regression loss function, and a calibration loss function that takes into account precision and confidence. The method outputs a calibrated image with the object bounding box, the corresponding label, and a respective confidence score, in which the confidence score is a probability associated with the predicted class label.

A system for performing artificial intelligence (AI)-based customized storytelling video generation includes a story designer AI agent, a storyboard generator AI agent, a video creator AI agent, an agent manager AI agent, and an observer AI agent. Coordinated by the agent manager AI agent, the agents collaboratively process a textual prompt and a reference video provided by a user to generate a multi-shot video depicting a story of a customized subject from the reference video. The story designer, agent manager, and observer AI agents leverage Large Language Models (LLMs), while the storyboard generator AI agent employs a three-step pipeline of generation, removal, and redrawing to maintain character detail consistency across video shots. The video creator AI agent utilizes a Latent Diffusion Model (LDM) based Image-to-Video (I 2 V) model to ensure intra-shot character detail consistency. The system achieves high-quality, coherent storytelling videos with customizable subject fidelity.

A method of determining a management strategy and implementing core actions for a cooling system includes obtaining data stream data, including at least one of a weather data stream, a power grid data stream, a social network data stream, a satellite data stream, and a climate model data stream; obtaining historical data including at least one of historical weather data, historical power grid data, historical social network data, historical satellite data, and historical climate model data; determining features from the data stream data and the historical data to generate collected feature data; determining patterns from the collected feature data to generate pattern data; generating policy data including candidate setpoints; determining a set of actions based on the policy data; and transmitting the set of actions and the candidate setpoints.

A method and system for video instance segmentation includes a recurrent encoder-based network trained by knowledge distillation from a transformer encoder. Real time performance is achieved by replacing the transformer encoder with the trained recurrent encoder for inference. The system includes a video camera to capture a sequence of video frames, a machine learning processing engine for video instance segmentation, and a video output for outputting a sequence of mask instances. The machine learning processing engine is configured with an interchangeable encoder module. During inference, the encoder module is configured with a recurrent encoder having a combination of convolutional and recurrent layers, The recurrent layers capture temporal relationships between the video frames. During training, the encoder module is configured with a teacher transformer encoder for training the recurrent encoder as a student through knowledge distillation. A transformer decoder outputs video instance mask predictions.

A data augmentation method and system for generating enriched training images using diffusion models, hybrid concatenation, and fractal blending. An original image and at least one prompt are input to a diffusion model to generate a corresponding image. A hybrid image is formed by concatenating a portion of the original image with a remaining portion of the generated image, wherein concatenation is performed using a binary pixel-wise mask. The mask comprises pixels valued at zero or one, with at least one entire row or column set to zero. The concatenation includes multiplying pixels of the original image with the mask and multiplying pixels of the generated image with the complement of the mask. A fractal image is blended into the hybrid image using a blending factor to produce an augmented image.

Disclosed are a method and system to protect user facial privacy against unknown face recognition levels without compromising on a user's online experience. An input source to input an original face image. A training circuit configured to train a generator model to output an image that resembles the original face image. An optimizer configured to generate a protected face image based on the trained model that fools a black-box face recognition model, while imitating a makeup style. A display device to display the protected face image online.

A system, computer-readable storage medium and method for prognosis of head and neck cancer, includes an input for receiving electronic health records (EHR) of a patient, an input for receiving multimodal images of a head and neck area of the patient, a feature extraction module for converting the electronic health records and multimodal images into at least one feature vector, a hybrid machine learning architecture that includes a multi-task logistic regression (MTLR) model and a multi-layer artificial neural network, the hybrid architecture takes as input the at least one feature vector and outputs a final risk score of prognosis for head and neck cancer for the patient.

A method and system are arranged for fact checking electronically posted claims. The system includes an input/output device for inputting a textual complex claim as a natural language statement with a combination of two or more facts and outputting an indication that the textual complex claim is true or false. A processor connected to the input/output device generates, by a program generation module, a reasoning program for the input complex claim as a sequence of reasoning steps, where each step directs to a function in a set of sub-task functions. The processor generates, by a program execution module, each step in the reasoning program to a respective sub-task function and executes the respective sub-task function in order to provide the outputted indication.

A unified framework system and method for a computer implemented artificial intelligent assistant to perform multiple tasks for remote sensing, includes a task input field for receiving a task identity, a global image encoder configured to receive a remote-sensing image and a user query and encode patch-level tokens at a high resolution via interpolation positional encodings, an MLP adapter configured to receive the patch-level tokens and adapt the tokens to language space, and a large language model configured to generate natural language responses interleaved with corresponding object locations based on the language space and task specific prompts. The global image encoder further includes a region input field for receiving region location parameters. The framework system is configured to switch based on the input task identity between different types of remote sensing visual interpretation tasks.