Awesome-Foundation-Models curates a comprehensive list of foundation models for vision and language tasks, which are large-scale pretrained models adaptable to various downstream applications. This repository aims to organize and summarize recent research in this rapidly evolving field, particularly focusing on survey papers. It avoids including research papers without associated code, focusing on impactful and well-documented models.
This repository distinguishes itself through its focus on providing a curated list of recent survey papers, specifically highlighting publications from 2024 and 2025. It includes a detailed breakdown of papers by date, making it easy to track the latest advancements. Additionally, for each entry, it provides direct links to the papers and an indication of their popularity through GitHub star counts, fostering efficient discovery of relevant research.
- Survey Papers: Central focus on organizing and presenting survey papers covering recent progress in foundation models.
- Date-Based Organization: Structured listings categorized by year and month, facilitating tracking of recent developments.
- GitHub Integration: Provides direct links to paper sources and GitHub repositories for relevant models.
- Community-Driven: Actively updated with new publications, reflecting ongoing research in the field.
- Focus on Vision-Language: Specializes in models applicable to both vision and language tasks.
The repository is actively maintained, with frequent updates including new survey papers and releases each month. Demonstrated by continuous additions of recent publications, it is a relevant and up-to-date resource. The inclusion of GitHub star counts provide a sense of community interest and adoption of linked repositories.
This repository is valuable for researchers, developers, and students interested in understanding the current landscape of foundation models. It offers a curated starting point for exploring recent advancements, identifying key models, and tracking the evolution of this transformative technology. By organizing a dedicated list of papers and more, the project allows users to rapidly gain insights into the field and navigate the landscape of foundation models.