Commit
•
3f19727
1
Parent(s):
3751a2a
Update README.md
Browse files
README.md
CHANGED
@@ -7,14 +7,21 @@ library_name: ml-4m
|
|
7 |
|
8 |
# 4M: Massively Multimodal Masked Modeling
|
9 |
|
10 |
-
*
|
11 |
|
12 |
-
|
13 |
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
4M is a framework for training "any-to-any" foundation models, using tokenization and masking to scale to many diverse modalities.
|
17 |
-
Models trained using 4M can perform a wide range of vision tasks, transfer well to unseen tasks and modalities, and are flexible and steerable multimodal generative models.
|
|
|
18 |
|
19 |
|
20 |
## Installation
|
@@ -35,12 +42,19 @@ Please see https://github.com/apple/ml-4m/blob/main/README_GENERATION.md for mor
|
|
35 |
|
36 |
If you find this repository helpful, please consider citing our work:
|
37 |
```
|
38 |
-
@inproceedings{
|
39 |
title={{4M}: Massively Multimodal Masked Modeling},
|
40 |
author={David Mizrahi and Roman Bachmann and O{\u{g}}uzhan Fatih Kar and Teresa Yeo and Mingfei Gao and Afshin Dehghan and Amir Zamir},
|
41 |
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
|
42 |
year={2023},
|
43 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
```
|
45 |
|
46 |
## License
|
|
|
7 |
|
8 |
# 4M: Massively Multimodal Masked Modeling
|
9 |
|
10 |
+
*A framework for training any-to-any multimodal foundation models. <br>Scalable. Open-sourced. Across tens of modalities and tasks.*
|
11 |
|
12 |
+
[`Website`](https://4m.epfl.ch) | [`GitHub`](https://github.com/apple/ml-4m) | [`BibTeX`](#citation)
|
13 |
|
14 |
+
Official implementation and pre-trained models for :
|
15 |
+
|
16 |
+
[**4M: Massively Multimodal Masked Modeling**](https://arxiv.org/abs/2312.06647), NeurIPS 2023 (Spotlight) <br>
|
17 |
+
*[David Mizrahi](https://dmizrahi.com/)\*, [Roman Bachmann](https://roman-bachmann.github.io/)\*, [Oğuzhan Fatih Kar](https://ofkar.github.io/), [Teresa Yeo](https://aserety.github.io/), [Mingfei Gao](https://fly6464.github.io/), [Afshin Dehghan](https://www.afshindehghan.com/), [Amir Zamir](https://vilab.epfl.ch/zamir/)*
|
18 |
+
|
19 |
+
[**4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities**](https://arxiv.org/abs/2406.09406), arXiv 2024 <br>
|
20 |
+
*[Roman Bachmann](https://roman-bachmann.github.io/)\*, [Oğuzhan Fatih Kar](https://ofkar.github.io/)\*, [David Mizrahi](https://dmizrahi.com/)\*, [Ali Garjani](https://garjania.github.io/), [Mingfei Gao](https://fly6464.github.io/), [David Griffiths](https://www.dgriffiths.uk/), [Jiaming Hu](https://scholar.google.com/citations?user=vm3imKsAAAAJ&hl=en), [Afshin Dehghan](https://www.afshindehghan.com/), [Amir Zamir](https://vilab.epfl.ch/zamir/)*
|
21 |
|
22 |
4M is a framework for training "any-to-any" foundation models, using tokenization and masking to scale to many diverse modalities.
|
23 |
+
Models trained using 4M can perform a wide range of vision tasks, transfer well to unseen tasks and modalities, and are flexible and steerable multimodal generative models.
|
24 |
+
We are releasing code and models for "4M: Massively Multimodal Masked Modeling" (here denoted 4M-7), as well as "4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities" (here denoted 4M-21).
|
25 |
|
26 |
|
27 |
## Installation
|
|
|
42 |
|
43 |
If you find this repository helpful, please consider citing our work:
|
44 |
```
|
45 |
+
@inproceedings{4m,
|
46 |
title={{4M}: Massively Multimodal Masked Modeling},
|
47 |
author={David Mizrahi and Roman Bachmann and O{\u{g}}uzhan Fatih Kar and Teresa Yeo and Mingfei Gao and Afshin Dehghan and Amir Zamir},
|
48 |
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
|
49 |
year={2023},
|
50 |
}
|
51 |
+
|
52 |
+
@article{4m21,
|
53 |
+
title={{4M-21}: An Any-to-Any Vision Model for Tens of Tasks and Modalities},
|
54 |
+
author={Roman Bachmann and O{\u{g}}uzhan Fatih Kar and David Mizrahi and Ali Garjani and Mingfei Gao and David Griffiths and Jiaming Hu and Afshin Dehghan and Amir Zamir},
|
55 |
+
journal={arXiv 2024},
|
56 |
+
year={2024},
|
57 |
+
}
|
58 |
```
|
59 |
|
60 |
## License
|