News

• Hire Me — Open to full-time Research Scientist roles in 2026. Connect with me on LinkedIn!
• My submission, BEHAVE: Behavioral Ethology for Human Assessment via Variational Encoding, has been accepted at the NeurIPS 2025 Workshop on Data on Brain and Mind (DBM).
• My paper, Brain Feature Maps Reveal Progressive Animal-Feature Representations, is published in Science Advances and featured as “When Neurons Discover on Their Own” by Harvard Brain Institute News.
• Check out my preprint on Behavioral Dynamics in Bipolar Disorder on medRxiv.
• Co-authored paper Arousal as a universal embedding for spatiotemporal brain dynamics now published in Nature.

About Me

Hi! I’m Victoria Zhanqi Zhang (张展旗), a Ph.D. candidate in Computer Science at UC San Diego, supported by the HDSI Ph.D. Fellowship. I’m co-advised by Dr. Mikio Aoi and Dr. Gal Mishne. I earned dual degrees in Computer Science and Electrical Engineering from Washington University in St. Louis, where I worked with Dr. Carlos Ponce as an undergraduate researcher.

I develop machine learning models to uncover structure and dynamics in complex behavioral and brain systems. My research bridges computational neuroscience and deep learning to understand how natural learning in the brain can inspire more robust, interpretable AI.

Computational Neuroscience — I study how neural representations and learning dynamics emerge across brain hierarchies using electrophysiological decoding, hierarchical modeling, and behavioral analysis. In Brain Feature Maps Reveal Progressive Animal-Feature Representations, I showed how hierarchical representations of animal features arise along the primate ventral visual stream. I also develop behavioral models to identify state-dependent dynamics in psychiatric disorders such as bipolar disorder (preprint).

Machine Learning — I build interpretable and robust models that learn from complex neural and behavioral data. My ongoing work explores how self-supervised and generative systems form hierarchical, multi-scale representations and decode behavior or speech from neural activity.

Industry Experience — During my internships at Meta, I worked on developing multimodal foundation models for neural wristband and visual data fusion in 2024, advancing hand recognition and handwriting decoding models. In 2025, I joined the team to work on handwriting recognition using electromyography (EMG) signals from the Meta Neural Band, which capture electrical activity from subtle forearm muscle movements to enable intuitive, gesture-based control and text input. The project was live demoed at Meta Connect 2025, and the Meta Neural Band was later recognized as one of TIME’s Best Inventions of 2025.

Explore my projects, publications, and CV. My blog features essays and learning notes on AI, neuroscience, and more.

Grew up in Jinan, China; moved to Beijing during my teens; began undergrad in St. Louis, MO in 2016; now based in San Diego, CA for grad school.

I love traveling, art, and animals! I live in a Disney dream with my free-flying birds: cockatiels Ashe and Pearl, and parakeet Kiwi. Check out my art portfolio.