mlbio-epfl/joint-inference

[ICLR 2025] Large (Vision) Language Models are Unsupervised In-Context Learners

40
/ 100
Emerging

This project helps machine learning practitioners improve the performance of existing large language models (LLMs) and vision-language models (VLMs) on specific tasks. You provide your chosen LLM or VLM along with a dataset, and the system uses an unsupervised adaptation framework to make the model perform better. This is useful for researchers and data scientists working with advanced AI models who want to enhance model accuracy without needing labeled ground truth data.

No commits in the last 6 months.

Use this if you need to boost the accuracy of your large language or vision-language models on tasks without access to costly labeled training data.

Not ideal if you are looking for a pre-trained model or a solution that does not require some technical expertise in machine learning model setup and execution.

natural-language-processing computer-vision large-language-models model-optimization unsupervised-learning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

22

Forks

6

Language

Python

License

MIT

Last pushed

Jun 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mlbio-epfl/joint-inference"

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