6 papers
Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization
Jiangweizhi Peng, Zhiwei Tang, Gaowen Liu +2
Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, th…
Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction
Ioannis Tsaknakis, Bingqing Song, Shuyu Gan +5
Large Language Models (LLMs) excel at producing broadly relevant text, but this generality becomes a limitation when user-specific preferences are required, such as recommending re…
Targeted Forgetting of Image Subgroups in CLIP Models
Zeliang Zhang, Gaowen Liu, Charles Fleming +2
Foundation models (FMs) such as CLIP have demonstrated impressive zero-shot performance across various tasks by leveraging large-scale, unsupervised pre-training. However, they oft…
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
Xun Xian, Ganghua Wang, Xuan Bi +5
Retrieval-Augmented Generation (RAG) has been empirically shown to enhance the performance of large language models (LLMs) in knowledge-intensive domains such as healthcare, financ…
Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model
Changchang Sun, Gaowen Liu, Charles Fleming +1
Conditional diffusion models have gained increasing attention since their impressive results for cross-modal synthesis, where the strong alignment between conditioning input and ge…
Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities
Kaiwen Cai, Zhekai Duan, Gaowen Liu +2
Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotatio…