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 distinguished professors Prof. Zhongjie Ba and Prof. Kui Ren.

My academic journey has been enriched by diverse experiences, including an internship at Microsoft Research. Under the expert guidance of Shuang Ma, I had the opportunity to delve into advanced researches in representation learning and contribute to innovative projects.

Currently, I am passionate about:

• (Primary) Generative Model and 3D reconstruction: efficiency, theory and its application to various domains.
• Perception for human activity understanding: self-supervised learning method that improves egocentric video understanding ability.
• Security problem of AI - Forgery detection: detecting and identifying fake (AI generated) content.

News

Publications

• (Under review) Masked Diffusion Models are Fast Distribution Learners
  Jiachen Lei, Qinglong Wang, Peng Cheng, Zhongjie Ba*, Zhan Qin, Zhibo Wang, Zhenguang Liu, Kui Ren
  Preprint Page: Link

• (Under review) SurrogatePrompt: Bypassing the Safety Filter of Text-To-Image Models via Substitution
  Zhongjie Ba, Jieming Zhong, Jiachen Lei, Peng Cheng, Kui Ren*
  Preprint Page: Link

Technical Reports

• "Masked Autoencoders for Egocentric Video Understanding @ Ego4D Challenge 2022"
  Jiachen Lei, Shuang Ma, Zhongjie Ba, Kui Ren
  Arxiv Link: Link

Awards and Achievements