Hi!
I am Xiang Li (李想), a PhD student at School of Computing, National University of Singapore, supervised by Prof. Kenji Kawaguchi. Prior to NUS, I completed my B.E. in Computer Science and Technology at Harbin Institute of Technology (Shenzhen) in June 2022, advised by Prof. Ruifeng Xu.
My research interests focus on trustworthy generative artificial intelligence — especially copyright violation and protection in diffusion models and large language models. I am also interested in exploring the memorization and creativity ability of generative models.
Preprints
LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
Xiang Li, Qianli Shen, Haonan Wang, Kenji Kawaguchi
NeurIPS SafeGenAI Workshop. 2024. [openreview]
Selected Publications
(*: equal contribution)
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Qianli Shen, Yezhen Wang, Zhouhao Yang, Xiang Li, Haonan Wang, Yang Zhang, Jonathan Scarlett, Zhanxing Zhu, Kenji Kawaguchi
NeurIPS. 2024. [arxiv]
VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models
Xiang Li*, Qianli Shen*, Kenji Kawaguchi
Few-Shot Aspect-Category Sentiment Analysis via Meta-Learning
Bin Liang*, Xiang Li*, Lin Gui, Yonghao Fu, Yulan He, Min Yang, Ruifeng Xu
Transactions on Information Systems. 2023. [paper]
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection
Bing Liang*, Qinglin Zhu*, Xiang Li*, Min Yang, Lin Gui, Yulan He, Ruifeng Xu
ACL. 2022. [paper]
Miscellaneous
- Interesting fact — the pronunciation of my name in Chinese also means “ideal”. People say “Ideal is the beacon, illuminating the directions of life”. Finding myself, knowing myself, and discovering the direction of my life. That’s probably the meaning my name has given me.
- In my spare time, I enjoy painting , reading , watching movies , photographing ……