SoM
Image marking tool
Enables visual grounding in large language models by overlaying spatial and speakable marks on images
Set-of-Mark Prompting for GPT-4V and LMMs
1k stars
23 watching
98 forks
Language: Python
last commit: 6 months ago Related projects:
Repository | Description | Stars |
---|---|---|
| A guide to using pre-trained large language models in source code analysis and generation | 1,789 |
| A large language model designed to process and generate visual information | 956 |
| A system that uses large language models to generate segmentation masks for images based on complex queries and world knowledge. | 1,923 |
| Trains multilingual image description models using neural sequence models and extracts hidden features from trained models. | 46 |
| An image annotation tool supporting various modes and formats, including CLS, DET, SEG, and PASCAL VOC. | 211 |
| Automatically embeds image files as Base64-encoded data into rendered HTML from Markdown source | 0 |
| Training and deploying large language models on computer vision tasks using region-of-interest inputs | 517 |
| Enables text rendering in popular data visualization packages using markdown | 80 |
| A markup language that combines elements from Markdown and DokuWiki to display text with formatting and structure | 16 |
| Tools for building machine learning solutions on satellite imagery | 81 |
| A tool for annotating images with tags and categories | 134 |
| A Vim plugin for syntax highlighting of Scalable Vector Graphics (SVG) files. | 9 |
| Improves Vim's highlighting of shell scripts by providing enhanced syntax support. | 7 |
| A LaTeX environment and code highlighting solution for showcasing Smalltalk code in documents. | 8 |
| A C++ port of the Scintilla text editing control to OpenGL, enabling 3D rendering and interaction. | 32 |