Bio

Welcome to my research page. I work on generative AI, adaptive control theory, and how to combine them to make robust tools for complex time-varying dynamic systems.

Bounded Extremum Seeking: Stabilizing and Optimizing Unknown Systems.

I invented an adaptive feedback algorithm known as Bounded Extremum Seeking which can optimize the outputs of or stabilize analytically unknown time-varying nonlinear dynamic systems with analytically unknown output functions.

Reference: Scheinker, Alexander. "Model independent beam tuning." Proceedings of the 2013 International Particle Accelerator Conference, Shanghai, China. 2013. Link to paper

And later proved this algorithm works with arbitrary measurable dithers (not required to be differentiable or continuous).

Reference: Scheinker, Alexander, and David Scheinker. "Bounded extremum seeking with discontinuous dithers." Automatica 69 (2016): 250-257. Link to paper

Autonomous Particle Accelerators: Adaptive Control of Particle Accelerators and Adaptive Machine Learning for Virtual Beam Diagnostics.

I have applied this algorithm to particle accelerators around the world (at LANL, SLAC, CERN, LBNL, BNL, and DESY) for autonomous beam tuning and virtual 6D beam diagnostics, and for material science applications for 3D dynamic imaging.

Reference: Scheinker, Alexander, et al. "Demonstration of model-independent control of the longitudinal phase space of electron beams in the linac-coherent light source with femtosecond resolution." Physical review letters 121.4 (2018): 044801. Link to paper

Reference: Scheinker, Alexander, et al. "Model-independent tuning for maximizing free electron laser pulse energy." Physical review accelerators and beams 22.8 (2019): 082802. Link to paper

Reference: Scheinker, Alexander. "Physics-constrained superresolution diffusion for six-dimensional phase space diagnostics." Physical Review Research 7.2 (2025): 023091. Link to paper

Reference: Scheinker, Alexander, et al. "PhaseFlow4D: Physically Constrained 4D Beam Reconstruction via Feedback-Guided Latent Diffusion." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026, pp. 4729-4737. Link to paper

Adpative Latent Space Tuning: Adaptive Control of Latent Space Dynamics.

I developed a method of adaptive latent space tuning, for controlling the latent dynamics of generative models, to make them robust for time-varying systems.

Reference: Scheinker, Alexander. "Adaptive machine learning for time-varying systems: low dimensional latent space tuning." Journal of Instrumentation 16.10 (2021): P10008. Link to paper

Bidirectional autoregressive models can predict their own rollout errors.

Recently, I developed a general method which allows generative autoregressive models to estimate their own rollout errors at test time when the ground truth is not available. This general method is applicable to generative diffusion models, flow models, and any other autoregressive rollout approach.

Reference: Scheinker, Alexander. "Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors." arXiv preprint arXiv:2608.00675 (2026). Link to paper

About Me

I have a PhD in Control Theory and Masters degrees in Math and Physics. I am the Adaptive Machine Learning Team Leader at Los Alamos National Laboratory and a Research Affiliate at Lawrence Berkeley National Laboratory.

Recent Work

Adaptive generative diffusion models for time-varying systems and round-trip consistency, a self-supervised test-time method for generative autoregressive models to predict their own rollout errors without access to ground truth.

Reference: Scheinker, Alexander. "Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors." arXiv preprint arXiv:2608.00675 (2026). Link to paper