Abstract: A method including receiving a user input for input to a language processing machine learning model (MLM). The method also includes generating modified inputs that are based on, and semantically related to, the user input. The method also includes executing the MLM to generate model outputs of the MLM. The MLM takes as input instances of each of the modified inputs. The method also includes sampling the model outputs using a statistical sampling strategy to generate sampled model outputs. The method also includes clustering the sampled model outputs into clusters. Each cluster of the clusters represents a distinct semantic meaning of the sampled model outputs. The method also includes generating a confidence metric for the user input. The confidence metric includes a predictive entropy of the clusters. The method also includes routing the user input based on whether the confidence metric satisfies or fails to satisfy a threshold value.

Abstract: Augmented Denoising Diffusion Implicit Models (“DDIMs”) using a latent trajectory optimization process can be used for image generation and manipulation using text input and one or more source images to create an output image. Noise bias and textual bias inherent in the model representing the image and text input is corrected by correcting trajectories previously determined by the model at each step of a diffusion inversion process by iterating multiple starts the trajectories to find determine augmented trajectories that minimizes loss at each step. The trajectories can be used to determine an augmented noise vector, enabling use of an augmented DDIM and resulting in more accurate, stable, and responsive text-based image manipulation.

Abstract: Systems and methods are disclosed for classifying objects by a machine learning (ML) model. The ML model includes one or more layer level classification models to generate classifications and uncertainty metrics in the classifications and a meta-model to generate a final classification and confidence based on the underlying classifications and uncertainty metrics. In some implementations, the ML model provides an object to be classified to one or more layer level classification models, and the layer level classification models generate a classification for the object and an uncertainty metric in the classification. The meta-model receives the classifications and uncertainty metrics from the one or more layer level classification models and generates the final classification and confidence in the final classification. The uncertainty metrics may also be output by the ML model or used to adjust the meta-model to improve the final classification and confidence.

Abstract: Systems and methods are disclosed for model based document image enhancement. Instead of requiring paired dirty and clean images for training a model to clean document images (which may cause privacy concerns), two models are trained on the unpaired images such that only the dirty images are accessed or only the clean images are accessed at one time. One model is a first implicit model to translate the dirty images from a source space to a latent space, and the other model is a second implicit model to translate the images from the latent space to clean images in a target space. The second implicit model is trained based on translating electronic document images in the target space to the latent space. In some implementations, the implicit models are diffusion models, such as denoising diffusion implicit models based on solving ordinary differential equations.

Abstract: Some embodiments provide a mechanism to automatically group workloads of a network into clusters of related workloads. The method of some embodiments displays consolidated workload data for a network. The method, for each of multiple workloads: (1) receives a set of identifiers characterizing the workload; and (2) converts the set of identifiers to a vector representation of the workload. The method then identifies clusters of workloads based on the vector representations of the workloads. The method then displays the workloads grouped in the identified clusters and displays data flows between the clusters of workloads. Converting the set of identifiers to a vector representation of the workload may include applying a similarity metric to the set of identifiers.

Abstract: In one set of embodiments, a host system can perform a random walk along a graph representing network traffic in a virtual network, where the virtual network comprises a plurality of virtual machines (VMs) running on a plurality of host systems including the host system, and where the random walk starts from a node of the graph corresponding to a VM running on the host system. The host system can further construct, based on the random walk, a local neighborhood of VMs associated with the VM and determine, based on the local neighborhood, whether the VM is a localized VM. Upon determining that the VM is not a localized VM, the host system can transmit a random walk data entry identifying the VM and the local neighborhood to a server communicatively coupled with the plurality of host systems.