Abstract: The present disclosure provides systems and methods for video generation using latent diffusion machine learning models. Given a text input, video data relevant to the text input can be generated using a latent diffusion model. The process includes generating a predetermined number of key frames using text-to-image generation tasks performed within a latent space via a variational auto-encoder, enabling faster training and sampling times compared to pixel space-based diffusion models. The process further includes utilizing two-dimensional convolutions and associated adaptors to learn features for a given frame. Temporal information for the frames can be learned via a directed temporal attention module used to capture the relation among frames and to generate a temporally meaningful sequence of frames. Additional frames can be generated via a frame interpolation process for inserting one or more transition frames between two generated frames.

Abstract: Automatic data generation includes extracting latent features from an input image, adding a perturbation to the latent features, applying the perturbed latent features to a pre-trained generative model, and training an image generator with images output from the generative model.

Abstract: The present invention discloses a shed tunnel structure for preventing a falling rock, including a shed tunnel body and a buffer plate for bearing impact of the falling rock, where the shed tunnel body includes a first supporting structure, and the first supporting structure is arranged on a side away from a ramp; one end of the buffer plate is connected to the ramp; a side face of the buffer plate close to the shed tunnel body is in movable contact with the first supporting structure, and the contact position is close to the other end of the buffer plate. The objective of resisting continuous impact of the falling rock can be achieved through the structural design.

Abstract: Generating an object using a diffusion model includes obtaining a first input and a second input, and synthesizing an output object from the first input and the second input. The synthesizing of the output object includes generating a layout of the output object from the first input, injecting the second input as a content conditioner to the layout of the output object, and de-noising the layout of the output object injected with the content conditioner to generate a content of the output object.

Abstract: Embodiments of the present disclosure relate to automated validation of medical data. Some embodiments of the present disclosure provide a method for medical data validation. The method comprises obtaining target medical data generated in a medical test and obtaining a machine learning model for validating medical data. The machine learning model represents an association between the medical data and validation results, the validation results indicating information about predetermined actions to be performed on the medical data. The method further comprises determining a target validation result for the target medical data by applying the target medical data to the machine learning model, the target validation result indicating information about a target action selected from the predetermined actions to be performed on the target medical data. Through the solution, it is possible to achieve automated medical data validation with high accuracy and efficiency as well as reduced manual efforts.

Abstract: Apparatuses, systems, and techniques to generate a robust representation of an image. In at least one embodiment, input tokens of an input image are received, and an inference about the input image is generated based on a vision transformer (ViT) system comprising at least one self-attention module to perform token mixing and a channel self-attention module to perform channel processing.

Abstract: A super-network comprising a plurality of layers may be generated. Each layer may comprise cells with different structures. A predetermined number of cells from each layer may be selected. A plurality of cells may be generated based on selected cells using a local mutation model, wherein the local mutation model comprises a mutation window for removing redundant edges from each selected cell. Performance of the plurality of cells may be evaluated using a differentiable fitness scoring function. The operations of the generating a plurality of cells using the local mutation model, the evaluating performance of the plurality of cells using the differentiable fitness scoring function and the selecting the subset of cells based on the evaluation results may be iteratively performed until the super-network converges. A search space for each layer may be generated based on a predetermined top number of cells with largest fitness scores after the super-network converges.