Update README.md
Browse files
README.md
CHANGED
|
@@ -7,25 +7,24 @@ datasets:
|
|
| 7 |
# NEPA: Next-Embedding Predictive Architectures Are Strong Vision Learners
|
| 8 |
|
| 9 |
[]()
|
| 10 |
-
[]()
|
| 11 |
-
[]()
|
| 12 |
|
| 13 |
-
This is a PyTorch/GPU re-implementation of Next-Embedding
|
| 14 |
|
| 15 |
<p align="center">
|
| 16 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/63f233820a16587ea967adc2/f3ybK_7Mf7rMekc05AcWH.png" width="350">
|
| 17 |
</p>
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
```
|
| 22 |
@article{six2025nepa,
|
| 23 |
-
title={Next-Embedding
|
| 24 |
author = {Sihan Xu and Ziqiao Ma and Wenhao Chai and Xuweiyi Chen and Weiyang Jin and Joyce Chai and Saining Xie and Stella X. Yu},
|
| 25 |
journal={arXiv preprint arXiv:},
|
| 26 |
year={2025}
|
| 27 |
}
|
| 28 |
-
|
| 29 |
```
|
| 30 |
|
| 31 |
|
|
|
|
| 7 |
# NEPA: Next-Embedding Predictive Architectures Are Strong Vision Learners
|
| 8 |
|
| 9 |
[]()
|
| 10 |
+
[](https://sihanxu.github.io/nepa)
|
| 11 |
+
[](https://huggingface.co/collections/SixAILab/nepa)
|
| 12 |
|
| 13 |
+
This is a PyTorch/GPU re-implementation of Next-Embedding Prediction Makes Strong Vision Learners.
|
| 14 |
|
| 15 |
<p align="center">
|
| 16 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/63f233820a16587ea967adc2/f3ybK_7Mf7rMekc05AcWH.png" width="350">
|
| 17 |
</p>
|
| 18 |
|
| 19 |
+
Next-Embedding Predictive Autoregression. An image is split into patches and embedded into a sequence. An autoregressive model predicts the next embedding from previous ones.
|
| 20 |
|
| 21 |
```
|
| 22 |
@article{six2025nepa,
|
| 23 |
+
title={Next-Embedding Prediction Makes Strong Vision Learners},
|
| 24 |
author = {Sihan Xu and Ziqiao Ma and Wenhao Chai and Xuweiyi Chen and Weiyang Jin and Joyce Chai and Saining Xie and Stella X. Yu},
|
| 25 |
journal={arXiv preprint arXiv:},
|
| 26 |
year={2025}
|
| 27 |
}
|
|
|
|
| 28 |
```
|
| 29 |
|
| 30 |
|