Prompt Customization
Prompt customization focuses on adapting pre-trained large language models (LLMs) and other AI models to specific tasks or user preferences, improving performance and mitigating issues like bias and adversarial attacks. Current research emphasizes techniques like fine-tuning, low-rank adaptation (LoRA), and embedding customization, often applied within diffusion models, to achieve personalized outputs in various domains, including image generation, 3D modeling, and conversational AI. This research is significant for enhancing the safety, efficiency, and usability of AI systems across diverse applications, from personalized education to robust industrial tools.
Papers
TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts
Yuxuan Xie, Tianhua Li, Wenqi Shao, Kaipeng Zhang
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
Jiahua Dong, Wenqi Liang, Hongliu Li, Duzhen Zhang, Meng Cao, Henghui Ding, Salman Khan, Fahad Shahbaz Khan