Zander W. Blasingame

2026

1. ICLR
   Workshop

   Stochastic Few-step Models

   Romeo Passaro, Zander W. Blasingame, Michael M. Bronstein, and Alexander Tong

   Presented at ICLR 2026 DeLTa and ReALM-GEN workshops

   Abs Bib OpenReview PDF

   Reward alignment for flow and diffusion models, via test-time steering or fine-tuning, often relies on sampling from conditional distributions induced by stochastic dynamics. In practice, this creates a computational bottleneck requiring expensive SDE simulation. Meanwhile, recent few-step accelerations for generative flows largely target deterministic dynamics and therefore do not directly address stochastic conditional sampling. We introduce stochastic few-step models, a framework for fast sampling from SDE-defined conditional distributions by mapping the conditional SDE to a deterministic ODE with matching marginals. Building on this formulation, we show that the resulting conditional ODEs can be effectively distilled into a single few-step model, enabling efficient conditional rollouts. Experiments on Gaussian-mixture and MNIST steering show that the resulting sampler provides accurate conditional samples to improve reward steering outperforming standard denoiser heuristics.

   @misc{passaro2026stochastic,
     title = {Stochastic Few-step Models},
     author = {Passaro, Romeo and Blasingame, Zander W. and Bronstein, Michael M. and Tong, Alexander},
     year = {2026},
     url = {https://openreview.net/forum?id=i31AUZF8kO},
   }

2. ICLR
   Workshop

   Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers

   Zander W. Blasingame, and Chen Liu

   Presented at ICLR 2026 DeLTa and ReALM-GEN workshops

   Abs arXiv Bib OpenReview PDF

   Diffusion models have quickly become the state-of-the-art for numerous generation tasks across many different applications. Encoding samples from the data distribution back into the models underlying prior distribution is an important task that arises in many downstream applications. This task is often called the inversion of diffusion models. Prior approaches for solving this task, however, are often simple heuristic solvers that come with several drawbacks in practice. In this work, we propose a new family of solvers for diffusion models by exploiting the connection between this task and the broader study of algebraically reversible solvers for differential equations. In particular, we construct a family of reversible solvers using an application of Lawson methods to construct exponential Runge-Kutta methods for the diffusion models. We call this family of reversible exponential solvers Rex. In addition to a rigorous theoretical analysis of the proposed solvers we also demonstrate the utility of the methods through a variety of empirical illustrations.

   @misc{blasingame2026rex,
     title = {Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers},
     author = {Blasingame, Zander W. and Liu, Chen},
     year = {2026},
     url = {https://openreview.net/forum?id=rHIUKCqPBZ},
   }

2025

1. NeurIPS ICML
   Workshop ICLR
   Workshop

   Greed is Good: A Unifying Perspective on Guided Generation

   Zander W. Blasingame, and Chen Liu

   Published at NeurIPS (2025)

   Presented at ICML 2025 EXAIT workshop and ICLR 2025 FPI workshop

   Abs arXiv Bib OpenReview PDF Poster Slides

   Training-free guided generation is a widely used and powerful technique that allows the end user to exert further control over the generative process of flow/diffusion models. Generally speaking, two families of techniques have emerged for solving this problem for gradient-based guidance: namely, posterior guidance (i.e., guidance via projecting the current sample to the target distribution via the target prediction model) and end-to-end guidance (i.e., guidance by performing backpropagation throughout the entire ODE solve). In this work, we show that these two seemingly separate families can actually be unified by looking at posterior guidance as a greedy strategy of end-to-end guidance. We explore the theoretical connections between these two families and provide an in-depth theoretical of these two techniques relative to the continuous ideal gradients. Motivated by this analysis we then show a method for interpolating between these two families enabling a trade-off between compute and accuracy of the guidance gradients. We then validate this work on several inverse image problems and property-guided molecular generation.

   @inproceedings{blasingame2025greed,
     title = {Greed is Good: A Unifying Perspective on Guided Generation},
     author = {Blasingame, Zander W. and Liu, Chen},
     booktitle = {NeurIPS},
     year = {2025},
     url = {https://openreview.net/forum?id=s14pdQgoLb},
     month = dec,
   }

2024

1. NeurIPS NeurIPS
   Workshop

   AdjointDEIS: Efficient Gradients for Diffusion Models

   Zander W. Blasingame, and Chen Liu

   Published at NeurIPS (2024)

   Presented at NeurIPS - New Frontiers in Adversarial Machine Learning

   Abs arXiv Bib OpenReview PDF Blog Code Poster Slides Website

   The optimization of the latents and parameters of diffusion models with respect to some differentiable metric defined on the output of the model is a challenging and complex problem. The sampling for diffusion models is done by solving either the probability flow ODE or diffusion SDE wherein a neural network approximates the score function or related quantity, allowing a numerical ODE/SDE solver to be used. However, naïve backpropagation techniques are memory intensive, requiring the storage of all intermediate states, and face additional complexity in handling the injected noise from the diffusion term of the diffusion SDE. We propose a novel method based on the stochastic adjoint sensitivity method to calculate the gradientwith respect to the initial noise, conditional information, and model parameters by solving an additional SDE whose solution is the gradient of the diffusion SDE. We exploit the unique construction of diffusion SDEs to further simplify the formulation of the adjoint diffusion SDE and use a change-of-variables to simplify the solution to an exponentially weighted integral. Using this formulation we derive a custom solver for the adjoint SDE as well as the simpler adjoint ODE. The proposed adjoint diffusion solvers can efficiently compute the gradients for both the probability flow ODE and diffusion SDE for latents and parameters of the model. Lastly, we demonstrate the effectiveness of the adjoint diffusion solvers onthe face morphing problem.

   @inproceedings{blasingame2024adjointdeis,
     author = {Blasingame, Zander W. and Liu, Chen},
     booktitle = {NeurIPS},
     editor = {Globerson, A. and Mackey, L. and Belgrave, D. and Fan, A. and Paquet, U. and Tomczak, J. and Zhang, C.},
     pages = {2449--2483},
     publisher = {Curran Associates, Inc.},
     title = {Adjoint{DEIS}: Efficient Gradients for Diffusion Models},
     url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/04badd3b048315c8c3a0ca17eff723d7-Paper-Conference.pdf},
     openreview = {https://openreview.net/forum?id=fAlcxvrOEX},
     volume = {37},
     year = {2024},
     month = dec,
   }