ShengYun (Anthony) Peng

CS PhD at Georgia Tech
Hi, I'm Anthony, a CS PhD at Georgia Tech working with Polo Chau. My research strengthens the generalization and robustness of machine learning, spanning vision models, LLMs, and VLMs. As steps towards this goal, I work on:
• Multimodal representation learning : foundation models for table recognition (UniTable, Table Transformer, Self-supervised Pretraining), efficient text embedding models (coming soon!), and structural health monitoring (system identification).
• Robust machine learning models : LLM landscape (LLM safety basin), robust CNN design principles (#1 on RobustBench CIFAR-10, BMVC Best Poster Award), and multi-task person tracking (SkeleVision).
I am fortunate to have collaborated with researchers, developers, scientists, and engineers at Georgia Tech, Meta, IBM Research, Intel Lab, ADP, UCLA.

Featured Publications

ShengYun Peng , Seongmin Lee, Xiaojing Wang, Raji Balasubramaniyan, Duen Horng Chau
NeurIPS TRL Workshop, 2024
ShengYun Peng , Pin-Yu Chen, Matthew Hull, Duen Horng Chau
NeurIPS, 2024
ShengYun Peng , Seongmin Lee, Xiaojing Wang, Raji Balasubramaniyan, Duen Horng Chau
AAAI SDU Workshop, 2024
ShengYun Peng , Seongmin Lee, Xiaojing Wang, Raji Balasubramaniyan, Duen Horng Chau
NeurIPS TRL Workshop, 2023
Mansi Phute, Alec Helbling, Matthew Hull, ShengYun Peng , Sebastian Szyller, Cory Cornelius, Duen Horng Chau
ICLR Tiny Papers Track, 2024
ShengYun Peng , Weilin Xu, Cory Cornelius, Matthew Hull, Kevin Li, Rahul Duggal, Mansi Phute, Duen Horng Chau, Jason Martin
BMVC, 2023
Nilaksh Das, ShengYun Peng , Duen Horng Chau
ECCV AROW Workshop, 2022
ShengYun Peng , LingFeng Yan, Bin He, Ying Zhou
Smart Structures and Systems, 2021