Abstract: A computer-implemented system and method relate to object discovery. The system and method include receiving a source image and generating input data by associating each pixel of the source image with predetermined phase values. An encoder encodes the input data to generate latent representation data in spherical coordinates. A decoder decodes the latent representation data to generate spherical reconstruction data of the source image. The spherical reconstruction data includes a radial component and a plurality of phase components. A reconstructed image is generated based at least on the radial component. The reconstructed image is a reconstruction of the source image.

Abstract: A computer-implemented system and method relate to anomaly detection. A first source image is obtained from a first image set and a second source image is obtained from a second image set of an in-distribution image dataset. A diffusion model generates a modified image using the first source image and the second source image. A non-anomalous label is automatically generated for the first source image. The non-anomalous label is also generated for the second source image. An anomalous label is generated for the modified image. A training dataset is created. The training dataset includes at least the first source image with the non-anomalous label, the second source image with the non-anomalous label, and the modified image with the anomalous label. A machine learning model is trained or fine-tuned using the training dataset. The machine learning model being configured to perform a task of anomaly detection.

Abstract: A computer-implemented system and method relate to anomaly detection. Latent code of a source image is obtained. The latent code is designated as a target image. Source embedding data is generated form the source image. Text data, which is of a different domain than that of the source image, is obtained. Text embedding data is generated from the text data. Additional embedding data is generated using the source embedding data and the text embedding data. The additional embedding data provides guidance for modifying the source image. A modified image is generated via an iterative process that includes at least one iteration, where each iteration includes at least (i) encoding the target image to generate target embedding data, (ii) generating updated embedding data by combining the target embedding data and the additional embedding data, (iii) decoding the updated embedding data to generate a new image, and (iv) assigning the new image as the target image and the modified image.

Abstract: Fine-tuning a base large language model (LLM) is provided. A fine tuning of a base LLM having pre-trained model weights is performed using a plurality of LoRA components each defining a trainable low-rank matrix, such that the low-rank matrices are trained to perform the fine tuning while the pre-trained model weights remain fixed. An ensemble is constructed using the plurality of LoRA components. One or more regularization techniques are performed to the LoRA components to counter overconfidence in the ensemble of LoRA components. The ensemble of LoRA components, as regularized, are utilized as a fine-tuned model of the base LLM.

Abstract: Splitting integrators are provided for fast sampling from a diffusion generative model. A stochastic differential equation (SDE) for the diffusion generative model is split into multiple terms, the multiple terms including deterministic components and random components. Each of the multiple terms is solved to perform a time-reversed noise process using a splitting integrator such that each of the multiple terms is solved separately. Alternating is performed between taking integration steps according to each of the multiple terms. The solving is repeated a desired quantity of steps to complete the time-reversed noise process.

Abstract: A method for predicting the time evolution of a variable x that is influenced by a given process. The method includes: proceeding from the history Vt for the time step t, k candidates xt+11, . . . , xt+1k are ascertained for the value xt+1 of the variable x in the time step t+1; for candidates xt+11, . . . , xt+1k, scores st+11, . . . , st+1k are ascertained in cooperation between a probabilistic model and a process model that represents prior knowledge about the given process; from the set of candidates xt+11, . . . , xt+1k, a proper subset xt+1i, i?I?{1, . . . , k}, is selected based on the associated scores st+11, . . . , st+1k; proceeding from new selected candidates xt+1i for the time step t+1, l candidates xt+21, . . . , xt+2l are ascertained for the value xt+2 of the variable x in the time step t+2.

Abstract: A wireless system includes a controller that is configured to measure a first Reference Signal Received Power (RSRP1) from a first carrier at a first time, measure a second Reference Signal Received Power (RSRP2) from a second carrier at a second time, annotate the RSRP1 to the first carrier and the RSRP2 to the second carrier, in response to the first time and the second time being within a contemporaneous period, associate the RSRP1 and RSRP2 to the contemporaneous period, create an N-Dimension vector of RSRP1 and RSRP2 at the contemporaneous period, process the N-Dimension vector via a trainable function to obtain a predicted data rate, and in response to the predicted data rate falling below a normal operating range threshold, operate the system in a low bandwidth mode.

Abstract: A simple and highly effective zero-shot anomaly detection approach is disclosed. The approach is compatible with a variety of established anomaly detection methods. The approach relies on training an anomaly detector, such as a neural network, on a meta-set in combination with batch normalization.

Abstract: A computer-implemented method of anomaly detection associated with graphical data includes receiving as input one or more input data sets, wherein the input data sets includes one or more graphs, utilizing a plurality of graph neural networks (GNNs) to identify an aggregate loss including a first loss and second loss associated with the input data set, wherein the aggregate loss is associated with embedding's of the GNNs, and outputting a notification associated with an anomaly detection when the first and second loss exceeds an anomaly-detection threshold.

Abstract: A computer-implemented system and method relate to object discovery. The system and method include receiving a source image and generating input data by associating each pixel of the source image with predetermined phase values. An encoder encodes the input data to generate latent representation data in spherical coordinates. A decoder decodes the latent representation data to generate spherical reconstruction data of the source image. The spherical reconstruction data includes a radial component and a plurality of phase components. A reconstructed image is generated based at least on the radial component. The reconstructed image is a reconstruction of the source image.

Abstract: A computer-implemented method of anomaly detection associated with graphical data includes receiving as input one or more input data sets, wherein the input data sets includes one or more graphs, utilizing a plurality of graph neural networks (GNNs) to identify an aggregate loss including a first loss and second loss associated with the input data set, wherein the aggregate loss is associated with embedding's of the GNNs, and outputting a notification associated with an anomaly detection when the first and second loss exceeds an anomaly-detection threshold.

Abstract: A computer-implemented method for a machine learning system includes receiving a input image, adding an initial phase to each pixel associated with the input image to create a complex number, sending the complex number to an encoder, wherein the encoder is configured to output a complex-valued latent representation to a decoder, utilizing the decoder, decompose the complex-valued latent representation into a complex-valued output including both a real part and an associated phase, computing a reconstruction error between the input image and the real part of the complex-valued output, wherein the reconstruction error is associated with model parameters associated with the system, and updating and outputting the model parameters associated with the system until a convergence threshold is obtained.

Abstract: A wireless system includes a controller that is configured to measure a first Reference Signal Received Power (RSRP1) from a first carrier at a first time, measure a second Reference Signal Received Power (RSRP2) from a second carrier at a second time, annotate the RSRP1 to the first carrier and the RSRP2 to the second carrier, in response to the first time and the second time being within a contemporaneous period, associate the RSRP1 and RSRP2 to the contemporaneous period, create an N-Dimension vector of RSRP1 and RSRP2 at the contemporaneous period, process the N-Dimension vector via a trainable function to obtain a predicted data rate, and in response to the predicted data rate falling below a normal operating range threshold, operate the system in a low bandwidth mode.

Abstract: A device control system includes a controller. The controller may be configured to, receive a data set of N samples that includes normal and unlabeled unidentified anomalous data samples, process, via a model, the data set to produce an anomaly score associated with each sample in the data set, rank the normal and anomalous data samples according to the anomaly score associated with each data sample to produce a ranked order, label a fraction ? of the N samples that have the highest scores with an anomaly label and the remaining samples with a normal label, retrain the model using all N samples, the labels, and a joint loss function, repeat the process, rank, label, and retrain steps until the ranked order and labels for all of the N samples do not change, and operate the device control system based on the trained model.

Abstract: A method of controlling a device includes receiving data from a first sensor, encoding, via parameters of an encoder, the data to obtain a latent observation (wt) for the data and an uncertainty vector (?wt) for the latent observation, processing the latent observation with a recurrent neural network to obtain a switching variable (st) which determines weights (?t) of a locally linear Kalman filter, processing the latent observation and the uncertainty vector with said locally linear Kalman filter to obtain updated mean of latent representation (?zt) and covariance of latent representation (?zt) of the Kalman filter, decoding the latent representation to obtain mean (?xt) and covariance of a reconstruction of the data (?xt) and outputting the reconstruction at a time t.

Abstract: A computer-implemented method utilizing a continuous discrete recurrent Kalman network, wherein the method includes receiving, at an encoder, an input from one or more sensors, wherein the input includes one or more time series data associating data at one or more points in time; outputting, to a Kalman filter, a latent observation and uncertainty estimate in response to the input at the encoder; determining a latent state prior and latent state posterior utilizing the Kalman filter; and outputting, via a decoder, a filtered observation utilizing at least the latent state posterior.

Abstract: A anomalous region detection method includes receiving time series data being grouped in patches, encoding, via parameters of an encoder, the data to obtain local latent representations, determining a representation loss from the local latent representations, transforming the local latent representations associated with each patch, via at least two local neural transformations, to a series of diverse transformed vector representations, determining a dynamic deterministic contrastive loss (DDCL) from the series of diverse transformed vector representations, combining the representation loss and the DDCL to obtain updated parameters, updating the parameters of the encoder with the updated parameters, scoring each of the series of the diverse transformed vector representations, via the DDCL, to obtain a diverse semantic requirement score associated with each patch, smoothing the diverse semantic requirement score to obtain a loss region, masking data associated with the loss region to obtain verified data, and o