NeuronCtrl: Geometry-Aware Safe Closed-Loop Generative Control for Neuronal Microenvironment Dynamics

Haowei Xu, Yixin Chen, Wanyi Fu, Hongbin Han, Zhaoheng Xie
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:140675-140728, 2026.

Abstract

Neuromodulation can be viewed as closed-loop control of high-dimensional spatiotemporal fields on irregular 3D morphologies, coupling membrane electrophysiology with ionic reaction–diffusion. This view supports high-rate feedback and systematic in-silico evaluation, yet is difficult in practice. Unlike classical PDE control with known equations on regular domains, neuronal microenvironments exhibit complex, often unknown biophysics on irregular shapes. High-fidelity simulators are too costly for real-time control with repeated planning. The discretized field is sparsely observed and must satisfy hard full-field safety constraints. We introduce NeuronCtrl, a modular operator-level framework for safe, closed-loop generative control of neuronal microenvironment dynamics. Given measurements, actions, and morphology, a history-conditioned observer infers the latent field, a morphology-aware neural operator predicts one-step dynamics, and a flow-matching conditional flow proposes actions conditioned on user preferences. Safety is enforced via complementary barrier-based mechanisms at both the action and field levels, with minimal intervention. When latency is critical, the multi-step generator is distilled into a single-step policy while retaining the same safety filter. Experiments across three high-fidelity 3D neuromodulation benchmarks spanning deep brain stimulation, extracellular reaction–diffusion control, and astrocytic potassium regulation demonstrate improved trade-offs among cost, safety, and latency. Code is available at https://github.com/HowieHsu0126/NeuronControl.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-xu26d, title = {{N}euron{C}trl: Geometry-Aware Safe Closed-Loop Generative Control for Neuronal Microenvironment Dynamics}, author = {Xu, Haowei and Chen, Yixin and Fu, Wanyi and Han, Hongbin and Xie, Zhaoheng}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {140675--140728}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/xu26d/xu26d.pdf}, url = {https://proceedings.mlr.press/v306/xu26d.html}, abstract = {Neuromodulation can be viewed as closed-loop control of high-dimensional spatiotemporal fields on irregular 3D morphologies, coupling membrane electrophysiology with ionic reaction–diffusion. This view supports high-rate feedback and systematic in-silico evaluation, yet is difficult in practice. Unlike classical PDE control with known equations on regular domains, neuronal microenvironments exhibit complex, often unknown biophysics on irregular shapes. High-fidelity simulators are too costly for real-time control with repeated planning. The discretized field is sparsely observed and must satisfy hard full-field safety constraints. We introduce NeuronCtrl, a modular operator-level framework for safe, closed-loop generative control of neuronal microenvironment dynamics. Given measurements, actions, and morphology, a history-conditioned observer infers the latent field, a morphology-aware neural operator predicts one-step dynamics, and a flow-matching conditional flow proposes actions conditioned on user preferences. Safety is enforced via complementary barrier-based mechanisms at both the action and field levels, with minimal intervention. When latency is critical, the multi-step generator is distilled into a single-step policy while retaining the same safety filter. Experiments across three high-fidelity 3D neuromodulation benchmarks spanning deep brain stimulation, extracellular reaction–diffusion control, and astrocytic potassium regulation demonstrate improved trade-offs among cost, safety, and latency. Code is available at https://github.com/HowieHsu0126/NeuronControl.} }
Endnote
%0 Conference Paper %T NeuronCtrl: Geometry-Aware Safe Closed-Loop Generative Control for Neuronal Microenvironment Dynamics %A Haowei Xu %A Yixin Chen %A Wanyi Fu %A Hongbin Han %A Zhaoheng Xie %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-xu26d %I PMLR %P 140675--140728 %U https://proceedings.mlr.press/v306/xu26d.html %V 306 %X Neuromodulation can be viewed as closed-loop control of high-dimensional spatiotemporal fields on irregular 3D morphologies, coupling membrane electrophysiology with ionic reaction–diffusion. This view supports high-rate feedback and systematic in-silico evaluation, yet is difficult in practice. Unlike classical PDE control with known equations on regular domains, neuronal microenvironments exhibit complex, often unknown biophysics on irregular shapes. High-fidelity simulators are too costly for real-time control with repeated planning. The discretized field is sparsely observed and must satisfy hard full-field safety constraints. We introduce NeuronCtrl, a modular operator-level framework for safe, closed-loop generative control of neuronal microenvironment dynamics. Given measurements, actions, and morphology, a history-conditioned observer infers the latent field, a morphology-aware neural operator predicts one-step dynamics, and a flow-matching conditional flow proposes actions conditioned on user preferences. Safety is enforced via complementary barrier-based mechanisms at both the action and field levels, with minimal intervention. When latency is critical, the multi-step generator is distilled into a single-step policy while retaining the same safety filter. Experiments across three high-fidelity 3D neuromodulation benchmarks spanning deep brain stimulation, extracellular reaction–diffusion control, and astrocytic potassium regulation demonstrate improved trade-offs among cost, safety, and latency. Code is available at https://github.com/HowieHsu0126/NeuronControl.
APA
Xu, H., Chen, Y., Fu, W., Han, H. & Xie, Z.. (2026). NeuronCtrl: Geometry-Aware Safe Closed-Loop Generative Control for Neuronal Microenvironment Dynamics. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:140675-140728 Available from https://proceedings.mlr.press/v306/xu26d.html.

Related Material