ShengYun Anthony Peng

CS PhD at Georgia Tech
Hi, I'm Anthony. I'm a CS PhD at Georgia Tech working with Polo Chau. My research strengthens the generalization and safety of machine learning.
My current work creates next-generation generative AI models that are safe and generalizable, spanning LLMs and VLMs. Previously, my training framework unification research, fusing training paradigms and objectives, produces state-of-the-art (SOTA) first-of-its-kind generalizable approach for document and table understanding. My discovery of fundamental architectural design principles governing the adversarial robustness of deep learning models produces SOTA results (#1 on RobustBench CIFAR-10) and Best Poster Award at BMVC.
I have collaborated with researchers, developers, and scientists at Georgia Tech, Intel Lab, ADP, UCLA, Tongji University, Shanghai Jiao Tong University, and Fudan University.

Featured Publications

ShengYun Peng , Seongmin Lee, Xiaojing Wang, Raji Balasubramaniyan, Duen Horng Chau
preprint 2024
ShengYun Peng , Seongmin Lee, Xiaojing Wang, Raji Balasubramaniyan, Duen Horng Chau
Association for the Advancement of Artificial Intelligence (AAAI) SDU Workshop 2024
ShengYun Peng , Seongmin Lee, Xiaojing Wang, Raji Balasubramaniyan, Duen Horng Chau
Neural Information Processing Systems (NeurIPS) TRL Workshop 2023
Mansi Phute, Alec Helbling, Matthew Hull, ShengYun Peng , Sebastian Szyller, Cory Cornelius, Duen Horng Chau
arXiv 2023
ShengYun Peng , Weilin Xu, Cory Cornelius, Matthew Hull, Kevin Li, Rahul Duggal, Mansi Phute, Duen Horng Chau, Jason Martin
British Machine Vision Conference (BMVC) 2023
Nilaksh Das, ShengYun Peng , Duen Horng Chau
European Conference on Computer Vision (ECCV) AROW Workshop 2022
ShengYun Peng , LingFeng Yan, Bin He, Ying Zhou
Smart Structures and Systems 2021