# yuewang-cuhk/awesome-vision-language-pretraining-papers

Recent Advances in Vision and Language PreTrained Models (VL-PTMs)

Repository: https://github.com/yuewang-cuhk/awesome-vision-language-pretraining-papers
Canonical: https://ross.abutalabs.com/products/awesome-vision-language-pretraining-papers
License Family: other
Topics: vision-and-language, pretraining, multimodal-deep-learning, bert, vl-ptms
Last push: 2022-08-19T04:55:18+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2352, "days_push": 1475, "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 1159, forks 104 (observed 2026-08-28T04:03:48.551260+00:00)

## What it is
A curated awesome-list of research papers on Vision and Language PreTrained Models (VL-PTMs), covering image-, video-, and speech-based multimodal pretraining. It organizes papers like ViLBERT, LXMERT, VL-BERT, and UNITER with links to arXiv and code repositories.

## Use cases
- find papers on vision-language pretraining
- survey multimodal transformer models like ViLBERT and UNITER
- research reading list for VL-PTMs
- find code implementations of multimodal pretraining models
- catch up on recent advances in vision-and-language models
- compare image, video, and speech pretraining approaches

## When to choose
- you need a curated bibliography of vision-language pretraining papers
- you are surveying multimodal pretraining research for a literature review
- you want quick links to papers and their official code

## When to avoid
- you need a runnable library or framework rather than a paper list
- you need up-to-date coverage of post-2021 multimodal LLM research
- you want tutorials or educational content instead of paper citations

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, nlp, computer-vision
- domain: artificial-intelligence, machine-learning, computer-vision, awesome-lists
- platform: cross-platform
- tags: awesome-list, multimodal, vision-language, pretraining, papers, vl-ptms, research-papers, natural-language-processing

## Member repositories
- yuewang-cuhk/awesome-vision-language-pretraining-papers (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:48.551260+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 2026-08-30T06:31:55.517033+00:00, confidence not recorded.
  - readme: https://github.com/yuewang-cuhk/awesome-vision-language-pretraining-papers (fetched 2026-08-28T04:03:48.551260+00:00, sha 4adeff7ae3e0)
- Data as of 2026-08-30T08:39:29.467469+00:00.