Tianze Liu

Papers

Total Citations

H-Index

About

Tianze Liu is an emerging researcher working at the intersection of neuroscience-inspired computing, robotics, and artificial intelligence, with a particular focus on neuromorphic systems and biologically plausible learning models. Liu's work centers on bridging the gap between biological cognition and machine intelligence by emulating the neural mechanisms underlying animal learning in real-world robotic platforms. A defining theme across Liu's research is the challenge of overcoming the limitations of conventional deep learning approaches — specifically their dependence on massive datasets and high power consumption — by drawing inspiration from how biological organisms, such as rodents, naturally acquire and generalize knowledge. Liu's most notable contributions include pioneering work on replicating associative learning behaviors observed in rats using neuromorphic robots navigating open-field environments. By deploying spatial cell models — computational analogues of biological place and grid cells — Liu's systems demonstrate adaptive, energy-efficient navigation that mirrors animal cognition. These studies, cited a combined three times since 2024, represent early but meaningful steps toward scalable, brain-inspired AI architectures. Though Liu's citation record reflects an early-career trajectory, the research addresses timely and significant questions in neuromorphic engineering, positioning Liu as a promising contributor to the future of embodied, biologically grounded artificial intelligence.