Fork the consciousness, or download the project and create your own.

Jinchang Zhang

School of Electrical and Computer Engineering, University of Georgia

Builder The claim is about what the hardware does, and the philosophy is left open

Jinchang Zhang is a robotics researcher at the University of Georgia working with Guoyu Lu on embodied control, legged locomotion, and biologically inspired communication architectures. His work addresses how distributed sensorimotor modules in a physical robot can coordinate under strict internal bandwidth budgets.

As first author of the September 2026 paper “FlyCNS: Connectome-Grounded Dynamic Sparse Communication for Embodied Control” (arXiv:2609.28816), Zhang extracted a directional effective-rank prior $(\tilde{p}^\uparrow, \tilde{p}^\downarrow)$ from the Drosophila central nervous system connectome and paired it with NeuroRoute, a Lagrangian primal-dual actor-critic router trained across 206.4 million environment interactions on a 12-joint Unitree Go1 quadruped. At a 25 percent communication budget, the connectome-guided router used only 1,755 to 1,823 bits per step out of 8,224 while reaching a 0.882 tracking score, outperforming periodic and unguided asymmetric baselines by wide margins.

Zhang’s profile is Builder, covered for translating insect connectome pathway organization into a quantitative, reproducible control law for embodied hardware.

Known for. FlyCNS connectome-grounded embodied control and NeuroRoute Lagrangian sparse communication for quadruped locomotion

Coverage on this site

Related researchers