Decoding Cortical Microcircuits: A Generative Model for Latent Space Exploration and Controlled Synthesis

Xingyu Liu, Yubin Li, Guozhang Chen
Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, PMLR 308:116-148, 2026.

Abstract

A central idea in understanding brains and building brain neural networks is that structure determines function. However, the brain’s connectome is a massively high-dimensional graph, making the direct investigation of its structure-function relationships computationally intractable. Therefore, identifying a compact, low-dimensional representation that captures the connectome’s essential structural organization is crucial for elucidating these relationships. The existence of such a representation is biologically plausible: the "genomic bottleneck" theory provides a strong basis for such a compressed developmental blueprint. We introduce a generative model to learn this underlying representation from detailed connectivity maps of mouse cortical microcircuits. Our model successfully captures the essential structural information of these circuits within a compressed latent space. We then associate specific network structures, as encoded in this latent space, with computational functions using reservoir computing tasks. Building on this, our methodology allows for the controllable generation of novel, synthetic microcircuits with desired structural features by navigating the learned latent space. This research paradigm establishes a computational testbed to systematically investigate the brain’s inherent structure-function relationships. The ability to generate diverse, bio-plausible circuits could inform the development of more advanced artificial neural networks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v308-liu26a, title = {Decoding Cortical Microcircuits: A Generative Model for Latent Space Exploration and Controlled Synthesis}, author = {Liu, Xingyu and Li, Yubin and Chen, Guozhang}, booktitle = {Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026}, pages = {116--148}, year = {2026}, editor = {Abbasi-Asl, Reza and Iqbal, Asim and Ito, Shinya and Arkhipov, Anton and Sanborn, Sophia}, volume = {308}, series = {Proceedings of Machine Learning Research}, month = {27 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v308/main/assets/liu26a/liu26a.pdf}, url = {https://proceedings.mlr.press/v308/liu26a.html}, abstract = {A central idea in understanding brains and building brain neural networks is that structure determines function. However, the brain’s connectome is a massively high-dimensional graph, making the direct investigation of its structure-function relationships computationally intractable. Therefore, identifying a compact, low-dimensional representation that captures the connectome’s essential structural organization is crucial for elucidating these relationships. The existence of such a representation is biologically plausible: the "genomic bottleneck" theory provides a strong basis for such a compressed developmental blueprint. We introduce a generative model to learn this underlying representation from detailed connectivity maps of mouse cortical microcircuits. Our model successfully captures the essential structural information of these circuits within a compressed latent space. We then associate specific network structures, as encoded in this latent space, with computational functions using reservoir computing tasks. Building on this, our methodology allows for the controllable generation of novel, synthetic microcircuits with desired structural features by navigating the learned latent space. This research paradigm establishes a computational testbed to systematically investigate the brain’s inherent structure-function relationships. The ability to generate diverse, bio-plausible circuits could inform the development of more advanced artificial neural networks.} }
Endnote
%0 Conference Paper %T Decoding Cortical Microcircuits: A Generative Model for Latent Space Exploration and Controlled Synthesis %A Xingyu Liu %A Yubin Li %A Guozhang Chen %B Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026 %C Proceedings of Machine Learning Research %D 2026 %E Reza Abbasi-Asl %E Asim Iqbal %E Shinya Ito %E Anton Arkhipov %E Sophia Sanborn %F pmlr-v308-liu26a %I PMLR %P 116--148 %U https://proceedings.mlr.press/v308/liu26a.html %V 308 %X A central idea in understanding brains and building brain neural networks is that structure determines function. However, the brain’s connectome is a massively high-dimensional graph, making the direct investigation of its structure-function relationships computationally intractable. Therefore, identifying a compact, low-dimensional representation that captures the connectome’s essential structural organization is crucial for elucidating these relationships. The existence of such a representation is biologically plausible: the "genomic bottleneck" theory provides a strong basis for such a compressed developmental blueprint. We introduce a generative model to learn this underlying representation from detailed connectivity maps of mouse cortical microcircuits. Our model successfully captures the essential structural information of these circuits within a compressed latent space. We then associate specific network structures, as encoded in this latent space, with computational functions using reservoir computing tasks. Building on this, our methodology allows for the controllable generation of novel, synthetic microcircuits with desired structural features by navigating the learned latent space. This research paradigm establishes a computational testbed to systematically investigate the brain’s inherent structure-function relationships. The ability to generate diverse, bio-plausible circuits could inform the development of more advanced artificial neural networks.
APA
Liu, X., Li, Y. & Chen, G.. (2026). Decoding Cortical Microcircuits: A Generative Model for Latent Space Exploration and Controlled Synthesis. Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, in Proceedings of Machine Learning Research 308:116-148 Available from https://proceedings.mlr.press/v308/liu26a.html.

Related Material