About
I am a Ph.D. candidate in Integrative Life Sciences (Physics) at Peking University, advised by Prof. Si Wu.
My research approaches AI from a cognitively inspired perspective, with a focus on world models, latent action models, and skill learning. I aim to develop embodied agents that learn generalizable abstract structures from unannotated sensory inputs without relying on language supervision, supporting efficient learning, robust generalization, and flexible decision-making for intelligent robotics.
I also work in computational neuroscience, including hippocampal-entorhinal circuit modeling, high-frequency oscillations in epilepsy, and perceptual learning.
Education
Selected Publications
View All →* Equal contribution·† Corresponding author
DiLA: Disentangled Latent Action World Models
Tianqiu Zhang*, Muyang Lyu*, Yufan Zhang, Fang Fang, Si Wu†
Forty-third International Conference on Machine Learning, 2026
HomepageStructure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model
Tianqiu Zhang*, Muyang Lyu*, Xiao Liu, Si Wu†
Forty-third International Conference on Machine Learning, 2026
HomepageTo learn or not to learn, that is the question—a feature-task dual learning model of perceptual learning
Xiao Liu, Muyang Lyu, Cong Yu†, Si Wu†
Advances in Neural Information Processing Systems, 2024
HomepageA Differentiable Approach to Multi-scale Brain Modeling
Chaoming Wang†, Muyang Lyu, Tianqiu Zhang, Sichao He, Si Wu†
ICML 2024 Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators, 2024
HomepageNews
2 papers have been accepted by ICML 2026 🎉
Presented DiLA at the Soochow University-Peking University Joint Symposium on Cognitive Science and Brain-Computer Interfaces.
Presented our perceptual learning work at the Center for Quantitative Biology Annual Meeting at Peking University.