Jinqi Luo
Google Scholar / GitHub / Email / Twitter

I am Jinqi Luo, a PhD student of Computer and Information Science (CIS) in the University of Pennsylvania (Penn), affiliated with GRASP Lab and IDEAS Center, advised by Prof. René Vidal and collaborating with Prof. Chris Callison-Burch. I obtained the Master's degree in the Robotics Institute (MSR) at the School of Computer Science in Carnegie Mellon University (CMU). I was affiliated with CMU Computer Vision Group, advised by Prof. Fernando De la Torre and Dr. Dong Huang. I obtained the Bachelor's degree of Computer Science (Highest Distinction) at Nanyang Technological University (NTU Singapore) advised by Prof. Jun Zhao. I have experiences at Amazon (intern), Alibaba Alipay (intern), UC Berkeley (visiting student), and Duke University (RA).


Research Interests

Recent Works

Concept Lancet: Image Editing with Compositional Representation Transplant
Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan, Hancheng Min, Chris Callison-Burch, René Vidal
CVPR 2025
[Project Page] [ArXiv] [GitHub]

PaCE: Parsimonious Concept Engineering for Large Language Models
Jinqi Luo*, Tianjiao Ding*, Kwan Ho Ryan Chan, Darshan Thaker, Aditya Chattopadhyay, Chris Callison-Burch, René Vidal
NeurIPS 2024
[Project Page] [ArXiv] [GitHub]

Zero-shot Model Diagnosis
Jinqi Luo*, Zhaoning Wang*, Chen Henry Wu, Dong Huang, Fernando De La Torre
CVPR 2023
[Project Page] [ArXiv] [GitHub] [MS Thesis at CMU]

LogiCity: Advancing Neural-Symbolic AI with Abstract Urban Simulation
Bowen Li, Zhaoyu Li, Qiwei Du, Jinqi Luo, Wenshan Wang, Yaqi Xie, Simon Stepputtis, Chen Wang, Katia Sycara, Pradeep Ravikumar, Alexander Gray, Xujie Si, Sebastian Scherer
NeurIPS 2024
[Project Page] [ArXiv] [GitHub]

Recent Advances in Adversarial Training for Adversarial Robustness
Tao Bai, Jinqi Luo, Jun Zhao, Bihan Wen, Qian Wang
IJCAI 2021
[ArXiv]

A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization
Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald, Jinqi Luo, Salma Tarmoun, Enrique Mallada, René Vidal
AISTATS 2025
[ArXiv]

ActivityGAN: Data Augmentation in Sensor-Based Human Activity Recognition
Xi'ang Li*, Jinqi Luo*, Rabih Younes
HASCA Best Paper Award, UbiComp Adjunct 2020
[ACM Portal]

Contextual Knowledge Pursuit for Faithful Visual Synthesis
Jinqi Luo, Kwan Ho Ryan Chan, Dimitris Dimos, and René Vidal
ECCV Workshop 2024
[ArXiv] [GitHub]

Generating Adversarial yet Inconspicuous Patches with a Single Image
Jinqi Luo, Tao Bai, Jun Zhao
AAAI 2021 (Abstract), IOTJ 2022 (Extended)
[ArXiv] [Honors Thesis at NTU]


Services and Activities