About Me

Hi! I am Li (Shawn) Li, a PhD student at Thomas Lord Department of Computer Science, University of Southern California, supervised by Prof. Yue Zhao.

Before my PhD study in the USA, I spent wonderful years in Singapore and cooperated with great professors. I served as a research associate at Nanyang Technological University, working with Prof. Aixin Sun. I earned my Master’s degree from National University of Singapore in 2024, where I contributed as a research intern under the guidance of Prof. Tat-Seng Chua and Prof. Roger Zimmermann. Prior to that, I successfully completed my Bachelor’s degree at TongJi University, China in 2022. My research interests are centered around multimodal learning, Out-of-Distribution detection, and information retrieval.

Research Interests

🛡️ Trustworthy and Robust Multimodal Foundation Models

Multimodal OOD Detection & Robust Representation Learning
⭐ CVPR 2025 Highlight WWW 2025
Efficient & Secure On-Device Multimodal Adaptation
ICCV 2025 TOMM 2024
Debiased & Structure-Aware Multimodal Representations
AAAI 2024 ICASSP 2024 ACM MM 2023
Multimodal Retrieval, Video Understanding & Graph-Based Reasoning
TMLR 2026 ICLR 2025 SIGIR-AP 2025 NeurIPS 2023 TOMM 2024

🤖 Secure and Reliable Large Language Models

Hallucination Mitigation via Causal & Retrieval-Based Reasoning
AAAI 2026 EMNLP 2025
Prompt Injection, Jailbreak Defense & Robust Evaluation
COLM 2025 arXiv 2026 arXiv 2026
LLM-based Anomaly Detection, OOD Detection & Benchmarking
ACL 2025 arXiv 2025

⚙️ Agentic, Interactive & Structure-Aware AI Systems

Agentic & Tool-Augmented LLM Systems
ICLR 2026 arXiv 2026
Dataset Construction, Benchmarks & Evaluation for Trustworthy AI
ICLR 2026 MTI-LLM@NeurIPS 2025 🏆 ACL 2025 ICSE 2022

News

2026.01 📄 Paper
Our paper "Charts Are Not Images: On the Challenges of Scientific Chart Editing" is accepted by ICLR 2026.
2026.01 📄 Paper
New paper on LLM prompt injection; see the preprint.
2025.09 🏆 Award
2025.08 📄 Paper
"Treble Counterfactual VLMs: A Causal Approach to Hallucination" accepted as Findings paper by EMNLP 2025.
2025.06 📄 Paper
"Secure On-Device Video OOD Detection Without Backpropagation" accepted by ICCV 2025.
2025.05 👔 Position
Joining Adobe Research as a Research Scientist Intern. Summer in San Jose!
2025.02 📄 Paper ⭐ Highlight
"DPU: Dynamic Prototype Updating for Multimodal OOD Detection" accepted as a Highlight Paper (Top 3.7%) by CVPR 2025.
2024.11 📄 Paper
"Backpropagation-Free Multi-modal On-Device Model Adaptation" accepted by ACM Transactions on Multimedia Computing, Communications and Applications.
2024.08 🎓 Milestone
Started PhD journey at USC.
2024.02 👔 Position
Joined S-Lab, NTU as a Research Associate.

Work Experiences

Research Scientist Intern
Adobe Research
05/2025 – 08/2025
San Jose, CA
Research Associate
S-Lab, Nanyang Technological University
Supervisor: Prof. Aixin Sun
02/2024 – 08/2024
Singapore

Selected Publications

please refer to google scholar page to check all my publications. (* Equal Contribution)

Defenses Against Prompt Attacks Learn Surface Heuristics
Li Li*, Chenxiao Yu*, Zhiyu Ni*, Hao Li, Charith Peris, Chaowei Xiao, Yue Zhao
Preprint  
Charts Are Not Images: On the Challenges of Scientific Chart Editing
Li Li, Ryan Rossi, Sungchul Kim, Sunav Choudhary, Franck Dernoncourt, Puneet Mathur, Zhengzhong Tu, Yue Zhao
ICLR 2026  
A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
Li Li, Peilin Cai, Ryan A. Rossi, Franck Dernoncourt, Branislav Kveton, Junda Wu, Tong Yu, Linxin Song, Tiankai Yang, Yuehan Qin, Nesreen K. Ahmed, Samyadeep Basu, Subhojyoti Mukherjee, Ruiyi Zhang, Zhengmian Hu, Bo Ni, Yuxiao Zhou, Zichao Wang, Yue Huang, Yu Wang, Xiangliang Zhang, Philip S. Yu, Xiyang Hu, Yue Zhao
MTI-LLM @ NeurIPS 2025 🏆 Spotlight Top 5.6%  
Treble Counterfactual VLMs: A Causal Approach to Hallucination
Li Li, Jiashu Qu, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, Yue Zhao
EMNLP 2025 Findings  
Secure On-Device Video OOD Detection Without Backpropagation
Li Li, Peilin Cai, Yuxiao Zhou, Zhiyu Ni, Renjie Liang, You Qin, Yi Nian, Zhengzhong Tu, Xiyang Hu, Yue Zhao
ICCV 2025  
DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
Li Li, Huixian Gong, Hao Dong, Tiankai Yang, Zhengzhong Tu, Yue Zhao
CVPR 2025 ⭐ Highlight Top 3.7%  |  UQ4CV @ CVPR 2025
Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration
Li Li*, Wei Ji*, Zheqi Lv*, Wenqiao Zhang, Mengze Li, Zhen Wan, Wenqiang Lei, Roger Zimmermann
TOMM (ACM TMMCA)  
Panoptic Scene Graph Generation with Semantics-prototype Learning
Li Li, Wei Ji, Yiming Wu, Mengze Li, You Qin, Lina Wei, Roger Zimmermann
AAAI 2024  
Domain-wise Invariant Learning for Panoptic Scene Graph Generation
Li Li, You Qin, Wei Ji, Yuxiao Zhou, Roger Zimmermann
ICASSP 2024  
Biased-Predicate Annotation Identification via Unbiased Visual Predicate Representation
Li Li*, Chenwei Wang*, You Qin, Wei Ji, Renjie Liang
ACM MM 2023  
On the Importance of Building High-quality Training Datasets for Neural Code Search
Zhensu Sun, Li Li, Yan Liu, Xiaoning Du, Li Li
ICSE 2022 🌟 Distinguished Paper Nomination  

Honors and Awards

🏆 Amazon PhD Fellowship 2025–2026
🎖️ Capital One Fellowship 2024–2025
🌟 ICSE 2022 Distinguished Paper Award Nomination (Top 19 papers)
🎓 AAAI 2024 Student Scholarship

Services

Program Committee / Reviewer
2026 CVPR, AAAI, ICML, ICLR, COLM, KDD, ECCV
2025 ICML, ICLR, ICCV, COLM, ICASSP, KDD, IJCNN, ACL ARR
2024 ACM MM, ECCV, ACL ARR
Journal Reviewer
IEEE Transactions on Image Processing
IEEE Transactions on Neural Networks and Learning Systems
IEEE Transactions on Multimedia
IEEE Transactions on Circuits and Systems for Video Technology
International Journal of Computer Vision
Other
Student Volunteer at ACM Web Conference (2024)

Educations

08/2024 - present

Doctor of Philosophy in Computer Science

University of Southern California, USA


2022.08 - 2024.02

Master of Science in Industry 4.0

National University of Singapore, Singapore


2018.08 - 2022.06

Bachelor of Engineering in Software Engineering

TongJi University, China