Yizi Zhang

Hello! I am a postdoctoral researcher at Stanford University, jointly working with the Neural Prosthetics Translational Lab and the Linderman Lab. I received my Ph.D. from Columbia University and was advised by Dr. Liam Paninski. My research focuses on developing foundation models for neural encoding and decoding, as well as brain–computer interfaces (BCIs). My long-term goal is to decode the brain’s internal representations of the world and uncover the computational principles underlying intelligence.

I enjoy working with people who are passionate about neuroscience and BCI. If you would like to get involved or learn more about my work, feel free to email me anytime.

Recent News

• 6/2026:
  • Invited talk at Neuralink: “Neural Encoding and Decoding at Scale.”
• 5/2026:
  • 🎓 Graduated with a PhD in Statistics from Columbia University.
  • Excited to join Stanford as a postdoctoral researcher in the Neural Prosthetics Translational Lab and the Linderman Lab.
• 1/2026:
  • 🎉 My first-authored paper was accepted at ICLR 2026: “Decoding inner speech with an end-to-end brain-to-text neural interface.”
  • 🎉 Our paper was accepted at ICLR 2026: “Self-supervised pretraining of vision transformers for animal behavioral analysis and neural encoding”.
  • 🚀 Excited to share that our team (BIT) earned 1st place on the Brain-to-Text 2024 benchmark and 3rd place (out of 463 teams) on Brain-to-Text 2025!
• 12/2025:
  • Gave a talk at the UC Davis Neuroprosthetics Lab Journal Club on “Building scalable and generalizable models for neural encoding and decoding.”
• 11/2025:
  • Gave a talk at the Chang Lab on “Building scalable and generalizable models for neural encoding and decoding.”
  • 🎉 My first-authored paper was published by the Neuron journal: “Exploiting correlations across trials and behavioral sessions to improve neural decoding”.
  • Gave a talk at the Linderman Lab and the Stanford Neural Prosthetics Translational Lab on “Building scalable and generalizable models for neural encoding and decoding.”
• 09/2025:
  • 🎉 Our paper was accepted at NeurIPS 2025: “Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets”.
• 05/2025 - 09/2025:
  • Worked on a summer internship at CTRL-Labs at Meta on EMG-based neural interfaces.
  • Gave a talk at The Final Frontier of AI Workshop hosted by Flatiron Institute in New York about “Building towards a brain-wide foundation model at single-cell, single-spike resolution”.
• 04/2025:
  • 🎉 My first-authored paper was accepted at ICML 2025 as a spotlight: “Neural Encoding and Decoding at Scale.”
• 03/2025:
  • Gave a talk at the Building a Foundation Model for the Brain Workshop at COSYNE in Montreal, Canada on “Building towards a brain-wide foundation model at single-cell, single-spike resolution.”
• 11/2024:
  • Gave a talk at the Computational Machinery of Cognition Journal Club at the University of Tübingen in Germany on “Neural Encoding and Decoding at Scale.”
• 10/2024:
  • Gave a talk at the Computational Neuroscience Journal Club at Princeton University on “Towards a universal translator for neural dynamics at single-cell, single-spike resolution.”
• 09/2024:
  • 🎉 My first-authored paper was accepted at NeurIPS 2024: “Towards a ‘universal translator’ for neural dynamics at single-cell, single-spike resolution”.

Teaching

1. GR 8201 Statistical Analysis of Neural Data with Prof. Liam Paninski - Guest Lecturer
   • Neural Encoding and Decoding [Slides]
   • Self-Supervised Learning for Neurofoundation Models [Slides]

Mentorship

Co-mentored with Prof. Liam Paninski unless otherwise noted

• Tianxiao He, PhD, Computer Science and Engineering, NYU
• Hanrui Lyu, PhD, Statistics and Data Science, Northwestern University
• Jingyan Shen (with Dr. Yongchan Kwon), PhD, Computer Science, NYU
• Yanchen Wang, PhD, Computer Science, Stanford University
• Mia Dai, PhD, Statistics, Columbia University
• Qihang Jin, Research Assistant, Columbia University
• Tianshu Tan, PhD, Biomedical Engineering, Johns Hopkins University
• Baiyuan Chen, MPhil, Data Intensive Science, University of Cambridge