|
Research
I work on interdisciplinary study of AI and Social Science. On one hand, I investigate the societal impact of AI, including education, equality, policy, and more. On the other hand, I develop responsible AI and related techniques that mitigates negative societal consequences, prioritizing aspects such as safety, reliability, and privacy. My long-term goal is to comprehend and improve the relationship between AI and society.
Topics I currently focus on:
- Societal implication of AI.
Others:
|
|
Selected Publications and Preprints
(* joint first authors)
Full Publication List on Google Scholar.
|
Socially Responsible LLMs
Defending ChatGPT against Jailbreak Attack via Self-Reminder
Yueqi Xie*, Jingwei Yi*, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie, Fangzhao Wu
Nature Machine Intelligence, 2023
/
/
/
Media Coverage: TechXplore,
Tech Times,
News8Plus
|
GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis
Yueqi Xie, Minghong Fang, Renjie Pi, Neil Gong
Preprint, 2024
/
/
|
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Jingwei Yi*, Yueqi Xie*, Bin Zhu, Emre Kiciman, Guangzhong Sun, Xing Xie, Fangzhao Wu
Preprint, 2023
/
/
|
MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
Renjie Pi*, Tianyang Han*, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang
Preprint, 2024
/
/
|
Secure and Robust Federated Learning
DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics
Renjie Pi*, Weizhong Zhang*, Yueqi Xie*, Jiahui Gao, Xiaoyu Wang, Sunghun Kim, Qifeng Chen
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
/
/
|
Recommender Systems
Rethinking Multi-Interest Learning for Candidate Matching in Recommender Systems
Yueqi Xie, Jingqi Gao, Peilin Zhou, Qichen Ye, Yining Hua, Jaeboum Kim, Fangzhao Wu, Sunghun Kim
ACM Conference on Recommender Systems (RecSys), 2023
/
/
|
Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer
Network
Peiyan Zhang*, Jiayan Guo*, Chaozhuo Li*, Yueqi Xie, Jaeboum Kim, Yan Zhang, Xing Xie, Haohan Wang,
Sunghun Kim
ACM International WSDM Conference (WSDM), 2023
Best Paper Award Honorable Mention (Top 4/690)
/
/
|
Decoupled Side Information Fusion for Sequential Recommendation
Yueqi Xie*, Peilin Zhou* and Sunghun Kim
International ACM SIGIR Conference (SIGIR), 2022
/
/
|
Image Compression
Optimizing Image Compression via Joint Learning with Denoising
Ka Leong Cheng*, Yueqi Xie* and Qifeng Chen
European Conference on Computer Vision (ECCV), 2022
/
/
|
Enhanced Invertible Encoding for Learned Image Compression
Yueqi Xie*, Ka Leong Cheng* and Qifeng Chen
ACM International Conference on Multimedia (ACM MM), 2021
Full Oral Presentation (9% acceptance rate)
/
/
|
IICNet: A Generic Framework for Reversible Image Conversion
Ka Leong Cheng*, Yueqi Xie*, Qifeng Chen
International Conference on Computer Vision (ICCV), 2021
/
/
|
- WSDM 2023 Best Paper Award Honorable Mention
- Outstanding Graduate in Peking University, 2020
- Peking University Scholarship, 2018, 2019
|
|
