🧠 About Me
I am a Principal Scientist at NVIDIA Fundamental Generative AI Research (GenAIR) and a Visiting Researcher at Stanford University.
My research focuses on building the algorithmic foundations of generative AI—ranging from diffusion/flow models to physics-aware generation.
My work bridges theory and practice of generative learning to advance generative AI. I am deeply interested in both algorithmic/theoretical foundations of generative modeling, and its real-world applications across content creation, graphics, digital twins, science.
At NVIDIA, I lead core research on developing diffusion/flow-based foundation models for scientific AI, including digital twin of Earth for climate and weather simulations. I led the development of weather foundation models that have been integrated into NVIDIA products and adopted by major customers such as The Weather Channel.
📍 Bio
I earned my PhD in Electrical Engineering with a minor in Mathematics from the University of Minnesota, advised by Georgios Giannakis, focusing on statistical learning and optimization.
I was a Visiting Scholar at UC Berkeley’s RISE Lab with Michael Mahoney, and later a Postdoc and Research Associate at Stanford, working with David Donoho, John Pauly, and Shreyas Vasanawala on inverse problems and generative models.
I serve as an IEEE SPS Distinguished Industry Speaker, and a recipient of the IEEE SPS Young Author Best Paper Award.
📰 News
- October 2025 — Keynote at DigiAdvance (Aveiro, Portugal); invited talk at Instituto Superior Técnico (IST), Lisbon
- September 2025 — NeurIPS 2025 paper accepted: Test-Time Scaling of Diffusion Models via Noise Trajectory Search (arXiv)
- September 2025 — NeurIPS 2025 paper accepted: Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics (arXiv)
- May 2025 — ICML 2025 paper accepted: Adaptive Flow Matching for Resolving Small-scale Physics (link)
- March 2025 — Delivered colloquium talk at University of Minnesota (UMN): Steering Diffusion Models for Next-Gen AI
- January 2025 — Gave a Keynote at GTTI MMSP Meeting: Steering Diffusion Models for Next-Gen AI
- January 2025 — ICLR 2025 paper accepted: Heavy-Tailed Diffusion Models (link)
- January 2025 — ICLR 2025 paper accepted: Repulsive Latent Score Distillation (link)
- November 2024 — CorrDiff: Residual Diffusion for Science accepted at Nature Communications — Check out the paper, blog, or online demo
- September 2024 — Elected as IEEE Distinguished Industry Speaker
- September 2024 — Delivered invited talk at University of Rochester, NY: Steering Diffusion Models for Next-Gen AI
- May 2024 — NeurIPS 2024 paper accepted: Alias-free Diffusion Models (link)
💼 Opportunities
I am actively looking for PhD interns and collaborators interested in advancing generative modeling.
If you’re excited about building principled and impactful generative models, get in touch:
📧 mmardani@nvidia.com