Results 11 to 20 of about 1,137,884 (305)
The Power of Scale for Parameter-Efficient Prompt Tuning [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 In this work, we explore “prompt tuning,” a simple yet effective mechanism for learning “soft prompts” to condition frozen language models to perform specific downstream tasks.
Brian Lester +2 more
semanticscholar +1 more source
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing [PDF]
ACM Computing Surveys, 2021 This article surveys and organizes research works in a new paradigm in natural language processing, which we dub “prompt-based learning.” Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P(y|x),
Pengfei Liu +5 more
semanticscholar +1 more source
European Conference on Computer Vision, 2022 The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as an efficient and effective alternative to full fine-tuning for large-scale ...
Menglin Jia +6 more
semanticscholar +1 more source
Prompt-to-Prompt Image Editing with Cross Attention Control [PDF]
International Conference on Learning Representations, 2022 Recent large-scale text-driven synthesis models have attracted much attention thanks to their remarkable capabilities of generating highly diverse images that follow given text prompts.
Amir Hertz +5 more
semanticscholar +1 more source
Conditional Prompt Learning for Vision-Language Models [PDF]
Computer Vision and Pattern Recognition, 2022 With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets.
Kaiyang Zhou +3 more
semanticscholar +1 more source
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models [PDF]
arXiv.org, 2023 Recent years have witnessed the strong power of large text-to-image diffusion models for the impressive generative capability to create high-fidelity images.
Hu Ye +4 more
semanticscholar +1 more source
Large Language Models Are Human-Level Prompt Engineers [PDF]
International Conference on Learning Representations, 2022 By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However, task performance depends significantly on the quality of the prompt used to steer the model, and ...
Yongchao Zhou +6 more
semanticscholar +1 more source
Learning to Prompt for Continual Learning [PDF]
Computer Vision and Pattern Recognition, 2021 The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge.
Zifeng Wang +9 more
semanticscholar +1 more source
Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [PDF]
AISec@CCS, 2023 Large Language Models (LLMs) are increasingly being integrated into applications, with versatile functionalities that can be easily modulated via natural language prompts. So far, it was assumed that the user is directly prompting the LLM.
Kai Greshake +5 more
semanticscholar +1 more source
MaPLe: Multi-modal Prompt Learning [PDF]
Computer Vision and Pattern Recognition, 2022 Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well ...
Muhammad Uzair Khattak +4 more
semanticscholar +1 more source