About Me 👋
I am currently a Research Engineer at AMAP, Alibaba Inc, working on Video Generation. I hold an M.S. degree from Cyberspace Security Lab at Zhejiang University. During my time there, I had the privilege of being mentored by Professor Zhongjie Ba. My academic journey has been enriched by diverse experiences, including an internship at Microsoft Research under the expert guidance of Shuang Ma, as well as an internship in Professor Anima Anandkumar's group, where I had the privilege of receiving valuable support from Professor Anima Anandkumar, Julius Berner and Professor Chaowei Xiao.
Feel free to reach out: jiachenlei at zju dot edu dot cn or jiachenleiii at gmail dot com.
News
- Jan 2026 🎉 EPG was accepeted to ICLR 2026.
-
Oct 2025
Released
EPG
, bridging the gap between pixel and latent diffusion (1.58 FID on IN256) & consistency model (8.82 FID on IN256).EPG (2025)
There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training.
View on ArXiv → - Jan 2025 🎉 rRCM was accepted to ICLR 2025.
- Mar 2024 🎉 One paper on certified robustness accepted to NeurIPS 2024.
Selected Publications
There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
SurrogatePrompt: Bypassing the Safety Filter of Text-To-Image Models via Substitution
Education
Zhejiang University, Sep 2020 - April 2023
Shanghai University of Electric Power, Sep 2016 - July 2020