Boyang Zheng

I'm currently a senior-year student, a member of Shanghai Jiao Tong University, ACM Honor Class. I'm currently an intern at NYU VisionX Group, advised by Saining Xie.

My current research interests include computer vision, self-supervised learning, and multi-modal learning. I'm also interested at generative models, which are incredibly popular nowadays. In the realm of academic, I have little interest in chasing the state-of-the-art unless I have to. Instead, I prefer to explore intersting ideas that help better understanding of this field or could possibly lead to new applications. Apart from pure academic pursuit, I also devote myself to use AI for social good, such as copyright protection, fairness and so on. In this regard, I'm also a member of MIST, a project aiming to protect the copyrighted artworks.

Email  /  CV  /  Google Scholar  /  Github

News

[2024-5-1] Internship begins! I'm now an intern at NYU VisionX Lab, advised by Saining Xie, doing research on generative models and MLLMs. I'll be on site at July, see you in New York!

[2023-9-25] Internship begins! I'm now an intern at Shanghai AI Lab, advised by Chao Dong, doing research on MLLM and their possible applications on low-level vision tasks.

Publications

A careful designed framework to let a frozen LLM to perform low-level vision tasks without any multi-modal data or prior. We also find that most current MLLMs(2024.5) with generation ability are BLIND to low-level features.

A method to craft adversarial examples for Latent Diffusion Model against various personlization techniques(e.g. SDEdit, LoRA), strongly outperforming existing methods. We aim for protecting the privacy of artists and their copyrighted works in the era of AIGC.

This website is a modification of Jon Barron's Website.