Publications

• Yijing Zhang, Dyah Adila, Changho Shin, Frederic Sala. Personalize LLM: Fake it and Then Align. In submission to NAACL 2025. [Paper]
• Yijing Zhang, Frederic Sala. Methods for Domain-specific Fine-tuning for Generative Models. Senior honor thesis for Honors in the Major, L&S Honors Program at University of Wisconsin - Madison. [Paper]
• Lin Zhang, Shentong Mo, Yijing Zhang, Pedro Morgado. Audio-Guided Visual Animation. Accepted by European Conference on Computer Vision(ECCV) 2024. [Paper]
• Dyah Adila, Changho Shin, Yijing Zhang, Frederic Sala. Is Free Self-Alignment Possible? Preprint. In submission to International Conference on Learning Representations(ICLR) 2024. [Paper]
• Dyah Adila, Changho Shin, Yijing Zhang, Frederic Sala. Can Language Models Safeguard Themselves, Instantly and For Free? Accepted by International Conference on Machine Learning(ICML) 2024 Workshop on NextGenAISafety. [Paper]
• Lin Zhang, Yufan Zhou, Shentong Mo, Cheng-En Wu, Yibing Wei, Yijing Zhang, Jinhong Lin, Ruiyi Zhang, Tong Sun, Pedro Morgado. OpenASVA: Open-world Audio-Synchronized Visual Animation with Increased Controllability In process. Submission to Conference on Computer Vision and Pattern Recognition(CVPR) 2025。