Arash VAHDAT

DIFFUSION-BASED GENERATIVE MODELING FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS

COMPOSITIONAL TEXT-TO-IMAGE GENERATION WITH DENSE BLOB REPRESENTATIONS

DENOISING DIFFUSION GENERATIVE ADVERSARIAL NETWORKS

TECHNIQUES FOR IDENTIFICATION OF OUT-OF-DISTRIBUTION INPUT DATA IN NEURAL NETWORKS

LOSS-GUIDED DIFFUSION MODELS

VISION TRANSFORMER FOR IMAGE GENERATION

PHYSICS-GUIDED MOTION DIFFUSION MODEL

DIFFUSION-BASED OPEN-VOCABULARY SEGMENTATION

FAIRNESS-BASED NEURAL NETWORK MODEL TRAINING USING REAL AND GENERATED DATA

GENERATIVE MACHINE LEARNING MODELS FOR PRIVACY PRESERVING SYNTHETIC DATA GENERATION USING DIFFUSION

NEURAL NETWORK-BASED PERTURBATION REMOVAL

DATA SET GENERATION AND AUGMENTATION FOR MACHINE LEARNING MODELS

ADAPTIVE TOKEN DEPTH ADJUSTMENT IN TRANSFORMER NEURAL NETWORKS

Diffusion-based generative modeling for synthetic data generation systems and applications

DENOISING DIFFUSION GENERATIVE ADVERSARIAL NETWORKS

IMAGE GENERATION USING ONE OR MORE NEURAL NETWORKS

SCORE-BASED GENERATIVE MODELING IN LATENT SPACE

Score-based generative modeling in latent space

Techniques for identification of out-of-distribution input data in neural networks

TECHNIQUES TO IDENTIFY DATA USED TO TRAIN ONE OR MORE NEURAL NETWORKS

Differential privacy dataset generation using generative models

TRAINING ENERGY-BASED VARIATIONAL AUTOENCODERS

TRAINING A LATENT-VARIABLE GENERATIVE MODEL WITH A NOISE CONTRASTIVE PRIOR

ENERGY-BASED VARIATIONAL AUTOENCODERS

LATENT-VARIABLE GENERATIVE MODEL WITH A NOISE CONTRASTIVE PRIOR

DEEP HIERARCHICAL VARIATIONAL AUTOENCODER