Arash Vahdat

Affiliations

NVIDIA

papers

5,090

total citations

papers (29)

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

CVPR 2023arXiv

citations

Heavy-Tailed Diffusion Models

ICLR 2025arXiv

citations

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents

ICML 2024arXiv

citations

Truncated Consistency Models

ICLR 2025arXiv

citations

LANA: Latency Aware Network Acceleration

ECCV 2022arXiv

citations

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

CVPR 2025arXiv

citations

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

NEURIPS 2025arXiv

citations

ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

ICLR 2025arXiv

citations

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

ICLR 2025arXiv

citations

Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics

NEURIPS 2025arXiv

citations

A-ViT: Adaptive Tokens for Efficient Vision Transformer

CVPR 2022

citations

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

NEURIPS 2021

citations

Arash Vahdat

Affiliations

papers (29)

NVAE: A Deep Hierarchical Variational Autoencoder

Score-based Generative Modeling in Latent Space

LION: Latent Point Diffusion Models for 3D Shape Generation

See Through Gradients: Image Batch Recovery via GradInversion

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

PhysDiff: Physics-Guided Human Motion Diffusion Model

A Variational Perspective on Solving Inverse Problems with Diffusion Models

Contrastive Learning for Weakly Supervised Phrase Grounding

GENIE: Higher-Order Denoising Diffusion Solvers

DiffiT: Diffusion Vision Transformers for Image Generation

A Contrastive Learning Approach for Training Variational Autoencoder Priors

Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks

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

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

Energy-Based Diffusion Language Models for Text Generation

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

Compositional Text-to-Image Generation with Dense Blob Representations

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

Heavy-Tailed Diffusion Models

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents

Truncated Consistency Models

LANA: Latency Aware Network Acceleration

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

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

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

Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics

A-ViT: Adaptive Tokens for Efficient Vision Transformer

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

papers (29)

NVAE: A Deep Hierarchical Variational Autoencoder

Score-based Generative Modeling in Latent Space

LION: Latent Point Diffusion Models for 3D Shape Generation

See Through Gradients: Image Batch Recovery via GradInversion

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

PhysDiff: Physics-Guided Human Motion Diffusion Model

A Variational Perspective on Solving Inverse Problems with Diffusion Models

Contrastive Learning for Weakly Supervised Phrase Grounding

GENIE: Higher-Order Denoising Diffusion Solvers

DiffiT: Diffusion Vision Transformers for Image Generation

A Contrastive Learning Approach for Training Variational Autoencoder Priors

Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks

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

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

Energy-Based Diffusion Language Models for Text Generation

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

Compositional Text-to-Image Generation with Dense Blob Representations

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

Heavy-Tailed Diffusion Models

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents

Truncated Consistency Models

LANA: Latency Aware Network Acceleration

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

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

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

Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics

A-ViT: Adaptive Tokens for Efficient Vision Transformer

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