# uncbiag/Awesome-Foundation-Models

A curated list of foundation models for vision and language tasks

Repository: https://github.com/uncbiag/Awesome-Foundation-Models
Canonical: https://ross.abutalabs.com/products/awesome-foundation-models
License Family: other
Topics: foundation-models, vision-transformer, large-language-models, transformer-models, multimodal-models
Last push: 2026-04-20T12:10:42+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 35, longevity 89
- inputs: {"age_days": 1247, "days_push": 135, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1176, forks 62 (observed 2026-08-28T04:03:52.593784+00:00)

## What it is
An awesome-style curated list of foundation models—large pretrained models such as BERT, GPT-3, and DALL-E—for vision and language tasks. It catalogs research papers that include code, along with survey articles covering LLMs, vision transformers, and multimodal models.

## Use cases
- find a curated list of foundation models for vision and language tasks
- discover open-source large language models and vision transformers with code
- survey recent papers on multimodal and vision-language foundation models
- build a research reading list on pretrained foundation models
- locate surveys on image segmentation or video understanding with foundation models
- keep up with new survey papers on LLMs, diffusion models, and multimodal architectures

## When to choose
- you want a vetted directory of foundation model papers that include implementations
- you are starting research on vision-language, multimodal, or large language models
- you need survey papers on parameter-efficient fine-tuning, world models, or medical imaging foundation models

## When to avoid
- you need runnable software or model weights rather than a link list
- you want an inference or training toolkit instead of a literature index
- you are looking for papers without code, since those are explicitly excluded

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, computer-vision, nlp
- domain: awesome-lists, artificial-intelligence, machine-learning, deep-learning, large-language-models, computer-vision
- platform: -
- tags: awesome-list, foundation-models, curated-list, research-papers, survey, multimodal-models, vision-transformer, reading-list, papers-with-code, natural-language-processing

## Member repositories
- uncbiag/Awesome-Foundation-Models (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:52.593784+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:27:01.478935+00:00, confidence not recorded.
  - readme: https://github.com/uncbiag/Awesome-Foundation-Models (fetched 2026-08-28T04:03:52.593784+00:00, sha d3b88204e4ae)
- Data as of 2026-08-30T08:39:29.467469+00:00.