Prof. Andrew LUO

EDUCATION

• Ph.D. (Neural Computation & Machine Learning), Carnegie Mellon University
• Bachelor of Science in Computer Science, MIT

RESEARCH INTERESTS

Computational Cognitive Neuroscience, NeuroAI, Visual Perception, Generative Models, Machine Reasoning

My work focuses on understanding the computational principles underlying human visual perception and how these principles can inform the development of more intelligent machines. I use computational models, including deep generative models, to investigate how the brain processes visual stimuli and forms meaningful representations. Ultimately, I aim to bridge the gap between human and machine vision, leading to both a deeper understanding of human cognition and advancements in artificial intelligence.

RECENT PUBLICATIONS

Luo, A., Yeung, J., Zawar, R., Dewan, S., Henderson, M. M., Wehbe, L.*, Tarr, M. J.* (2024). Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers. In submission.

Dewan, S.*, Zawar, R.*, Saxena, P.*, Chang, Y., Luo, A., Bisk, Y. (2024). DiffusionPID: Interpreting Diffusion via Partial Information Decomposition. NeurIPS 2024.

Yin, J., Luo, A., Du, Y., Cherian, A., Marks, T. K., Le Roux, J., & Gan, C. (2024). Disentangled Acoustic Fields For Multimodal Physical Scene Understanding. Accepted to IROS 2024.

Luo, A., Henderson, M. M., Tarr, M. J., Wehbe, L. (2024) BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity. Accepted to ICLR 2024.

Luo, A., Henderson, M. M., Wehbe, L.*, Tarr, M. J.* (2023) Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models. Accepted to NeurIPS 2023 (oral, top 0.6% of submissions).

Luo, A., Du, Y., Tarr, M., Tenenbaum, J., Torralba, A., Gan, C. (2022) Learning Neural Acoustic Fields. Accepted to NeurIPS 2022.

Luo, A., Li, T., Zhang, W., Lee, T. (2021) SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators. Accepted to ICCV 2021.

Luo, A., Zhang, Z., Wu, J., W., Tenenbaum. (2020) End-to-End Optimization of Scene Layout. Accepted to CVPR 2020(oral).

RESEARCH OPPORTUNITIES:

I’m looking for motivated PhD, master’s, and undergraduate students with a strong background in computational modeling and machine learning to join my research group. And remote collaboration opportunities are also available. Please send an email to aluo@hku.hk with a copy of your CV and a short statement about your interests.