diff --git a/README.md b/README.md
index fb2ede334b1415eebc10fe5e8498c5f27304f88f..5852b044e6d36125cf5d94b93bfbe8ddad556f5c 100644
--- a/README.md
+++ b/README.md
@@ -10,15 +10,14 @@ Marc Szafraniec,
 Vasil Khalidov,
 Patrick Labatut,
 Armand Joulin,
-Piotr Bojanowski
+Piotr Bojanowski 
 
 [[`Paper`](https://arxiv.org/abs/2304.07193)] [[`Blog`](https://ai.facebook.com/blog/dino-v2-computer-vision-self-supervised-learning/)] [[`Demo`](https://dinov2.metademolab.com)] [[`BibTeX`](#citing-dinov2)]
 
-PyTorch implementation and pretrained models for DINOv2. For details, see the paper: **DINOv2: Learning Robust Visual Features without Supervision**.
+PyTorch implementation and pretrained models for DINOv2. For details, see the paper: **[DINOv2: Learning Robust Visual Features without Supervision](https://arxiv.org/abs/2304.07193)**.
 
 DINOv2 models produce high-performance visual features that can be directly employed with classifiers as simple as linear layers on a variety of computer vision tasks; these visual features are robust and perform well across domains without any requirement for fine-tuning. The models were pretrained on a dataset of 142 M images without using any labels or annotations.
 
-
 https://user-images.githubusercontent.com/60359573/230078733-5faffa19-e6ce-4c55-9200-62dd76f8236a.mp4
 
 <div align="center">
@@ -27,7 +26,7 @@ https://user-images.githubusercontent.com/60359573/230078733-5faffa19-e6ce-4c55-
 
 ## Pretrained models
 
-<table>
+<table style="margin: auto">
   <tr>
     <th>model</th>
     <th># of<br />params</th>
@@ -65,7 +64,6 @@ https://user-images.githubusercontent.com/60359573/230078733-5faffa19-e6ce-4c55-
   </tr>
 </table>
 
-
 ### Pretrained models via PyTorch Hub
 
 Please follow the instructions [here](https://pytorch.org/get-started/locally/) to install the PyTorch and torchvision dependencies (these are the only required dependencies). Installing both PyTorch and torchvision with CUDA support is strongly recommended.
@@ -188,7 +186,7 @@ python dinov2/run/eval/linear.py \
 
 We release the weights from evaluating the different models:
 
-<table>
+<table style="margin: auto">
   <tr>
     <th>model</th>
     <th>ImageNet<br />top-1</th>