Arash Vahdat

Arash Vahdat is a research director at NVIDIA Research, leading the fundamental generative AI research (GenAIR) team. Arash’s early work focused on generative AI models, including diffusion models, and their latent extensions with applications to image, video, text, weather, protein, and small molecule drug discovery. Arash obtained his doctorate from Simon Fraser University in Canada and was a research scientist at D-Wave Systems before joining NVIDIA in 2019.
Avatar photo

Posts by Arash Vahdat

Agentic AI / Generative AI Jan 27, 2026

Accelerating Diffusion Models with an Open, Plug-and-Play Offering

Recent advances in large-scale diffusion models have revolutionized generative AI across multiple domains, from image synthesis to audio generation, 3D asset... 8 MIN READ
Agentic AI / Generative AI Sep 23, 2025

Reasoning Through Molecular Synthetic Pathways with Generative AI

A recurring challenge in molecular design, whether for pharmaceutical, chemical, or material applications, is creating synthesizable molecules. Synthesizability... 7 MIN READ
Agentic AI / Generative AI Jan 13, 2025

Evaluating GenMol as a Generalist Foundation Model for Molecular Generation

Traditional computational drug discovery relies almost exclusively on highly task-specific computational models for hit identification and lead optimization.... 8 MIN READ
Agentic AI / Generative AI Apr 26, 2024

Enhance Text-to-Image Fine-Tuning with DRaFT+, Now Part of NVIDIA NeMo

Text-to-image diffusion models have been established as a powerful method for high-fidelity image generation based on given text. Nevertheless, diffusion models... 10 MIN READ
Computer Vision / Video Analytics Apr 26, 2022

Improving Diffusion Models as an Alternative To GANs, Part 2

This is part of a series on how researchers at NVIDIA have developed methods to improve and accelerate sampling from diffusion models, a novel and powerful... 16 MIN READ
Computer Vision / Video Analytics Apr 26, 2022

Improving Diffusion Models as an Alternative To GANs, Part 1

This is part of a series on how NVIDIA researchers have developed methods to improve and accelerate sampling from diffusion models, a novel and powerful class... 8 MIN READ