Arash Vahdat

32

Papers

617

Total Citations

Papers (32)

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

NeurIPS 2017arXiv

A Variational Perspective on Solving Inverse Problems with Diffusion Models

Energy-Based Diffusion Language Models for Text Generation

Heavy-Tailed Diffusion Models

Truncated Consistency Models

BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations

Not-So-Optimal Transport Flows for 3D Point Cloud Generation

Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks

See Through Gradients: Image Batch Recovery via GradInversion

A-ViT: Adaptive Tokens for Efficient Vision Transformer

Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models

A Robust Learning Approach to Domain Adaptive Object Detection

PhysDiff: Physics-Guided Human Motion Diffusion Model

Contrastive Learning for Weakly Supervised Phrase Grounding

LANA: Latency Aware Network Acceleration

Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models

Compositional Text-to-Image Generation with Dense Blob Representations

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents

Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel

A Hierarchical Deep Temporal Model for Group Activity Recognition

Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors

NVAE: A Deep Hierarchical Variational Autoencoder

On the distance between two neural networks and the stability of learning

A Contrastive Learning Approach for Training Variational Autoencoder Priors

Score-based Generative Modeling in Latent Space

Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence

Controllable and Compositional Generation with Latent-Space Energy-Based Models

LION: Latent Point Diffusion Models for 3D Shape Generation

GENIE: Higher-Order Denoising Diffusion Solvers

DVAE++: Discrete Variational Autoencoders with Overlapping Transformations