OliverRensu/ARM

[ICLR2025] This repository is the official implementation of our Autoregressive Pretraining with Mamba in Vision

25
/ 100
Experimental

This project offers a way to significantly improve how Mamba-based vision models learn and perform. By using an autoregressive pretraining method, it takes raw image datasets and produces highly accurate Mamba models for various computer vision tasks. This is for machine learning engineers and researchers building and deploying advanced vision systems.

No commits in the last 6 months.

Use this if you are working with Mamba architectures in computer vision and need to achieve higher accuracy and better scaling performance for your models, especially on large image datasets.

Not ideal if you are looking for an out-of-the-box solution for general image recognition without needing to pretrain or fine-tune models.

computer-vision deep-learning image-recognition model-pretraining vision-models
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

90

Forks

3

Language

Python

License

Last pushed

May 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OliverRensu/ARM"

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