GenAIR Group

GenAIR Group

Fundamental Generative AI Research (GenAIR) Group

Welcome to the homepage of NVIDIA’s Fundamental Generative AI Research (GenAIR) group, led by Arash Vahdat. We are part of the Learning and Perception Research (LPR) organization and mostly focus on generative learning and its applications in different areas. We are particularly interested in:

  • Generative AI for Proteins and Molecules: protein generation, binder design, molecule generation and optimization, etc.
  • Generative AI for Weather: weather downscaling, forecasting, etc.
  • Compositionality and Control: semantic and modular image, video, protein, and molecule generation and editing, etc.
  • Fundamental Research: discrete generative models, diffusion models, flow matching, accelerated sampling, equivariant models, etc.

We are currently looking for outstanding candidates to join our team as a research scientist. Please see this link for the current opening.

News

Jan 2024 - GenMol a generalist generative model for molecular tasks was announced at J.P. Morgan conference. Check out our paper, blog, or online demo for GenMol.

December 2024 - We’ll present 5 papers at NeurIPS in Vancouver!

December 2024 - We’ll present 2 papers at SIGGRAPH Asia in Tokyo!

November 2024 - The GenAIR website goes live!!

Current and Past Interns

Publications

Quickly discover relevant content by filtering publications.