Jinqi Luo

Google Scholar / GitHub / Email / Twitter

I am Jinqi Luo, a PhD student of Computer and Information Science in the University of Pennsylvania, 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. 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 (Rufus LLM intern), Alibaba (Alipay intern), UC Berkeley (visiting student), and Duke University (RA).

Research Interests

I focus on deep generative modeling and trustworthy AI. Specifically, I am working on controllability, robustness, and multimodality in foundation models. My work also emphasizes the curation of more informative and comprehensive data.
Please feel free to reach out by email. I am open to discussing emergent directions, potential collaborations, and opportunities.

Recent Works

Full publication list can be found here.

		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 (Google Scholar ranks it as top 10 cited in IJCAI) [ArXiv]
		Reliable and Responsible Foundation Models Xinyu Yang, Junlin Han, Rishi Bommasani, Jinqi Luo, Wenjie Qu, Wangchunshu Zhou, Adel Bibi, Xiyao Wang, Jaehong Yoon, Elias Stengel-Eskin, Shengbang Tong, Lingfeng Shen, Rafael Rafailov, ... (33 More Authors), Chris Callison-Burch, René Vidal, Filippos Kokkinos, Mohit Bansal, Beidi Chen, Huaxiu Yao TMLR 2025 [Paper Page]
		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]
		Voyaging into Perpetual Dynamic Scenes from a Single View Fengrui Tian, Tianjiao Ding, Jinqi Luo, Hancheng Min, René Vidal ICCV 2025 [Project Page] [ArXiv] [GitHub]
		SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations Buyun Liang, Liangzu Peng, Jinqi Luo, Darshan Thaker, Kwan Ho Ryan Chan, René Vidal NeurIPS 2025 [ArXiv] [GitHub]
		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

Conference Reviewer: CVPR, NeurIPS, ICLR, ICML, ICCV, EMNLP, ACL ARR, AISTATS, AAAI, ECCV.
Journal Reviewer: TMLR, Neurocomputing, TNNLS.
Organizer: ICLR FM-Wild Workshop.
Teaching Assistant: [Penn 23Fall] Deep Generative Models (Founding Members). [Penn 24Fall] Deep Generative Models.