Awesome Vision + Language
A curated list of recent research papers and resources on Vision and Language Pre-trained Models (VL-PTMs).
What is Awesome Vision + Language?
awesome-vision-language-pretraining-papers is a curated GitHub repository that aggregates recent research papers, code, and resources on Vision and Language Pre-trained Models (VL-PTMs). It provides a structured overview of multimodal AI models that learn joint representations from visual and textual data, facilitating tasks like visual question answering, image captioning, and cross-modal retrieval. The repository serves as a living survey, tracking progress from early models like ViLBERT to contemporary foundation models.
AI researchers, graduate students, and machine learning engineers working on multimodal learning, computer vision, or natural language processing who need a consolidated reference for state-of-the-art VL-PTM literature.
It saves significant literature review time by offering a meticulously organized, modality-wise taxonomy of papers with direct links to arXiv and code. Unlike generic paper lists, it focuses specifically on pretrained vision-language models, includes task-specific adaptations, and points to critical analysis studies.
Overview
Recent Advances in Vision and Language PreTrained Models (VL-PTMs)
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
