Awesome-Prompting-on-Vision-Language-Model

Why we included this project

If you are researching prompt engineering for vision-language models, this list is a practical entry point. It gathers papers from the accompanying survey and groups them by model type: those that generate text from images, those that match images to text like CLIP, and those that generate images from text. Each entry records the venue, year, a link to code when available, and a short comment on the prompting approach, which helps you scan a large bibliography quickly and pick works relevant to your task. The survey's distinction between hard and soft prompts, along with categories such as in-context learning and chain-of-thought prompting, gives useful shorthand when deciding which technique to try first. This is a literature map rather than runnable software, but it saves time when you are scoping a project in this area.