Zigeng Chen | National University of Singapore

About Me

I am an incoming Ph.D. student at Learning and Vision (LV) LAB @ National University of Singapore, advised by professor Xinchao Wang. Before joining the LV Lab, I earned my Bachelor’s degree in Communication Engineering from Soochow University and my Master’s degree in Electrical Engineering from the National University of Singapore. My current research interests focus on Efficient Generative AI.

Research Interests

Efficient AI: model compression, model acceleration, distributed computing.
Generative Model: diffusion models, large language models, mutimodal models.
Low-level Vision: computational photography, super-resolution.

News

[Sep. 2024] One first-auther paper about distributed acceleration of diffusion model is accepted to NeurIPS 2024.
[Sep. 2024] One first-auther paper about SAM compression is accepted to NeurIPS 2024.
[April. 2024] One first-auther paper about learnable ISP is accepted to IJCAI 2024.

Publications

NeurIPS

AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

Zigeng Chen, Xinyin Ma, Gongfan Fang, Zhenxiong Tan, Xinchao Wang*

The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).

PDF Code Project Page BibTex

NeurIPS

SlimSAM: 0.1% Data Makes Segment Anything Slim

Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang*

The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).

PDF Code BibTex

IJCAI

MetaISP: Efficient RAW-to-sRGB Mappings with Merely 1M Parameters

Zigeng Chen, Chaowei Liu, Yuan Yuan, Michael Bi Mi, Xinchao Wang*

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24).

PDF BibTex