Zijin Gu

I am currently a Machine Learning Researcher at Apple MLR. Previously I spent one wonderful year as an AIML resident.

I obtained my PhD at Cornell University in 2023, where I was very fortunate to be advised by Amy Kuceyeski and Mert Sabuncu. I worked on NeuroAI, an intersection between neuroscience and artifical intelligence.

I got my bachelor's degree at Zhejiang University om 2019, where I studied power electronics and digital/analog circuit design.

Email  |  Google Scholar  |  Github  |  LinkedIn  |  Twitter

profile photo

Photo taken in May 2023 during my graduation ceremony at Cornell.

Research Interest

I am fancisanted by the commonalities and differences in the structure and function of human brain and how each individual brain preceives and interacts with the world. And I believe computational methods, such as statistical and machine learning models, are powerful tools to dig deeper into this.

Now my research focuses more on speech and language processing, where my residency helped me switched the gear. I build scalable sequential models to assist speech recognition/generation and language modeling. I am more interested in understanding their working principles than just making things work.


General Publications
Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition
Zijin Gu, Tatiana Likhomanenko, He Bai, Erik McDermott, Ronan Collobert, and Navdeep Jaitly.
ArXiv 2024



Selected Neuroscience Publications
Machine learning and neuroimaging: Understanding the human brain in health and disease
Zijin Gu, Keith Jamison, Mert Sabuncu, and Amy Kuceyeski.
Chapter of Computational and Network Modeling of Neuroimaging Data 2024
Human brain responses are modulated when exposed to optimized natural images or synthetically generated images
Zijin Gu, Keith Jamison, Mert Sabuncu, and Amy Kuceyeski.
Communications Biology 2023
Decoding natural image stimuli from fMRI data with a surface-based convolutional network
Zijin Gu, Keith Jamison, Amy Kuceyeski, and Mert Sabuncu.
(Oral) Medical Imaging with Deep Learning 2023
Personalized visual encoding model construction with small data
Zijin Gu, Keith Jamison, Mert Sabuncu, and Amy Kuceyeski.
Communications Biology 2022
NeuroGen: Activation optimized image synthesis for discovery neuroscience
Zijin Gu, Keith Jamison, Meenakshi Khosla, Emily J. Allen, Yihan Wu, Ghislain St-Yves, Thomas Naselaris, Kendrick Kay, Mert Sabuncu, and Amy Kuceyeski.
NeuroImage 2022
Heritability and interindividual variability of regional structure-function coupling
Zijin Gu, Keith Jamison, Mert Sabuncu, and Amy Kuceyeski.
Nature Communications 2021



Website source from Jon Barron.

Last Updated: July 14th 2024.