Zander W. Blasingame

Postdoctoral Researcher @ Clarkson University, Potsdam NY, USA

zwblasingame.jpg

I am currently a postdoctoral researcher at Clarkson University studying inference-time control of flow/diffusion models. Lately, I’ve been interested in neural differential equations, score-based generative models, rough path theory for ML, and applications in ai4science. Recent research has focused on bespoke ODE/SDE solvers for the gradients of diffusion models, greedy algorithms for guided generation, and reversible solvers for diffusion models. Previously, I received my Ph.D. in Electrical and Computer Engineering from Clarkson University in 2025 supervised by Dr. Chen Liu.

All of Christ, for all of life.

In my free time I am an opposite hitter for the Clarkson Men’s Club Volleyball team. Additionally, I enjoy any form of barbell training and other power sports.

Latest News

Oct 10, 2025 Our new pre-print Rex: Reversible Solvers for Diffusion Models is now available on arXiv.
Sep 18, 2025 Our paper Greed is Good: A Unifying Perspective on Guided Generation was accepted @ NeurIPS 2025
Jul 29, 2025 Presented our paper of Scalable Malware Detection Framework Using Performance Counters and Gradient Boosting at the 36th IEEE International Conference on Application-specific Systems, Architectures and Processors conference in Vancouver, Canada
Jul 19, 2025 Presented our paper Greed is Good: A Unifying Perspective on Guided Generation at the The Exploration in AI Today Workshop @ ICML 2025 in Vancouver, Canada
Jul 03, 2025 Published a new preprint LoRA as a Flexible Framework for Securing Large Vision Systems

Latest Posts

Selected Publications

  1. AdjointDEIS: Efficient Gradients for Diffusion Models
    Zander W. Blasingame, and Chen Liu
    In Advances in Neural Information Processing Systems, Dec 2024
  2. Rex: Reversible Solvers for Diffusion Models
    Zander W. Blasingame, and Chen Liu
    Oct 2025
  3. Greed is Good: A Unifying Perspective on Guided Generation
    Zander W. Blasingame, and Chen Liu
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, Dec 2025