Short Bio
I’m currently a PhD student at School of Computer Science, Peking University, under the supervision of Prof. Yonghong Tian. I closely collaborate with Dr. Wei Fang of MiroMind, and Prof. Zhengyu Ma of Peng Cheng Laboratory. My research interests include spiking neural networks, AI infra, and AI for psychology.
- 2019.09 - 2023.07: bachelor of science, School of Electronic Engineering and Computer Science, Peking University
- 2020.09 - 2023.07: minor in psychology, School of Psychological and Cognitive Sciences, Peking University
- 2024.07 - 2025.07: visiting student, Peng Cheng Laboratory
- 2023.09 - present: PhD student, School of Computer Science, Peking University
Publications
First-author Papers
- Yifan Huang, Wei Fang, Zecheng Hao, Zhengyu Ma, Yonghong Tian, Towards Lossless Memory-efficient Training of Spiking Neural Networks via Gradient Checkpointing and Spike Compression, ICLR 2026 snn ai-infra
Preprints
- Yifan Huang, Wei Fang, Zhengyu Ma, Guoqi Li, Yonghong Tian, Scalable Dendritic Modeling Advances Expressive and Robust Deep Spiking Neural Networks, arXiv 2025 snn
Others
- Kaiwei Che, Wei Fang, Peng Xue, Yifan Huang, Zhengyu Ma, Yonghong Tian, Parallel Training Time-to-First-Spike Spiking Neural Networks, AAAI 2026 snn
- Zecheng Hao, Yifan Huang, Zijie Xu, Wenxuan Liu, Yuanhong Tang, Zhaofei Yu, Tiejun Huang, Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model, CVPR 2026 (in press) snn
- Kaiwei Che, Wei Fang, Zhengyu Ma, Yifan Huang, Peng Xue, Li Yuan, Yonghong Tian, Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch, ICML 2026 (spotlight, in press) snn
- Dongyang Ma, Zhengyu Ma, Yifan Huang, Chenlin Zhou, Wei Zhang, Yonghong Tian, Bio-Vision-Inspired Spiking Neural Networks for Object Detection with Event Cameras, ICML 2026 (in press) snn
Projects
- SpikingJelly: an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch. I am the main contributor and maintainer of SpikingJelly after 2024.07. snn
- depression-detection: the final coursework for PKU’s AI in Mental Health. ai4psyc
- tex-stripper: a simple tool to strip LaTeX commands from the document, so that the document can be checked by Grammarly.
- metropolis-pku: a delicate beamer theme for Peking University, modified from Metropolis.
- pku-cover-letter-latex: a cover letter template for Peking University.
- sysy-compiler: A simple compiler for PKU’s Compiler Principle course, implemented in Rust.