I study computational neuroscience. I use deep generative models, optimization methods, and differential geometry to investigate visual representations in the brain and in the neural networks.

Quick Bio

• I am currently a NeuroAI research fellow inKempner Institute for the Study of Natural and Artificial Intelligence.
• I obtained my Ph.D. in Neuroscience in 2023, working with professorCarlos R. Ponce at Harvard Medical School.
  • The lab originated at Washington University, and we moved from Washington University to HMS in 2021.
• I obtained B.S. in Physics at Peking University, in Yuanpei College, advised by theoretical neuroscientistLouis Tao.
• Myacademic website with my teaching slides, tutorials and papers.
• Mypersonal website with my notes on math, ML, and fun projects!

PinnedLoading

1. DiffusionFromScratchDiffusionFromScratchPublic

   Rebuild the Stable Diffusion Model in a single python script. Tutorial for Harvard ML from Scratch Series

   Python 219 15

2. TransformerFromScratchTransformerFromScratchPublic

   Tutorial for Harvard Medical School ML from Scratch Series: Transformer from Scratch. Demo the usage of transformer in various domains: Music sheet, audio signal, image generation & discrimination

   Python 45 7

3. GAN-GeometryGAN-GeometryPublic

   Official Code for ICLR2021 paper "A Geometric Analysis of Deep Generative Image Models and Its Applications"

   Jupyter Notebook 47 6

4. NotionArxivChat-CLINotionArxivChat-CLIPublic

   A few CLI tools to immersively, browse, read Arxiv paper, save to notion & zotero, chat with them and save the chat history

   Python 11 1

5. GPT-Auto-Data-AnalyticsGPT-Auto-Data-AnalyticsPublic

   Automatize local data analysis with team of tool-using GPT agents

   Jupyter Notebook 15 2

6. ActMax-Optimizer-DevActMax-Optimizer-DevPublic

   The official repo for GECCO 2022 paper High-Performance Evolutionary Algorithms for Online Neuronal Control in vivo and in silico

   Python 8 4