4 papers
Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message
Wei Duan, Li Qian
The rise of conversational interfaces has greatly enhanced LLM usability by leveraging dialogue history for sophisticated reasoning. However, this reliance introduces an unexplored…
MD-Face: MoE-Enhanced Label-Free Disentangled Representation for Interactive Facial Attribute Editing
Xuan Cui, Yunfei Zhao, Bo Liu +2
GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one face attribute unintentiona…
U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning
Bo Liu, Xuan Cui, Run Zeng +5
Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction sy…
IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring
Xuan Cui, Huiyue Li, Run Zeng +5
As large language models (LLMs) scale to billions of parameters, full-parameter fine-tuning becomes compute- and memory-prohibitive. Parameter-efficient fine-tuning (PEFT) mitigate…