Victorwz/VaLM

VaLM: Visually-augmented Language Modeling. ICLR 2023.

23
/ 100
Experimental

This project helps researchers in natural language processing (NLP) develop and evaluate language models that can 'see' as well as read. You would input large datasets of text and images, and it outputs a trained language model capable of more accurate language understanding and generation by integrating visual information. Researchers focused on advancing multimodal AI would find this useful.

No commits in the last 6 months.

Use this if you are an AI researcher looking to build and experiment with next-generation language models that leverage visual context to understand and generate text more effectively.

Not ideal if you need an out-of-the-box solution for specific image-text tasks like image captioning or visual question answering without deep model development.

natural-language-processing computer-vision multimodal-ai language-model-research ai-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

56

Forks

3

Language

Python

License

Last pushed

Mar 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Victorwz/VaLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.