📝 update README and project page

Author: Justin900429

README.md

@@ -4,7 +4,8 @@
 
 <p><strong>A unified cross-domain diffusion model for various makeup tasks</strong></p>
 
-<a href="#license-and-citation">
+<a href="https://arxiv.org/abs/2504.02545"><img src="https://img.shields.io/badge/arXiv-2504.02545-<color>"></a>
+<a href="#citation">
   <img alt="License: Apache2.0" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg"/>
 </a><br/><br/>
 
@@ -15,6 +16,7 @@
 > Bo-Kai Ruan, Hong-Han Shuai
 >
 > * Contact: Bo-Kai Ruan
+> * [arXiv paper](https://arxiv.org/abs/2504.02545) | [Project Website](https://basiclab.github.io/MAD)
 
 ## 🚀 A. Installation
 
@@ -184,4 +186,15 @@ python app.py
 ┗ ...
 ```
 
-![gradio](assets/gradio.png)
+![gradio](assets/gradio.png)
+
+## Citation
+
+```bibtex
+@article{ruan2025mad,
+  title={MAD: Makeup All-in-One with Cross-Domain Diffusion Model},
+  author={Ruan, Bo-Kai and Shuai, Hong-Han},
+  journal={arXiv preprint arXiv:2504.02545},
+  year={2025}
+}
+```

docs/index.html

@@ -115,11 +115,11 @@ <h1 class="title is-2 publication-title">MAD: Makeup All-in-One with Cross-Domai
             <div class="column has-text-centered">
               <div class="publication-links">
                 <span class="link-block">
-                  <a href="#" class="external-link button is-normal is-rounded is-dark">
+                  <a href="https://arxiv.org/abs/2504.02545" class="external-link button is-normal is-rounded is-dark">
                     <span class="icon">
                       <i class="ai ai-arxiv"></i>
                     </span>
-                    <span>arXiv [WIP]</span>
+                    <span>arXiv</span>
                   </a>
                 </span>
                 <!-- Code Link. -->
@@ -205,7 +205,8 @@ <h2 class="title is-3">✨ A. Translation Pipeline</h2>
       <img src="static/images/pipeline.svg" , alt="pipeline"
         style=" display: block; margin-left: auto; margin-right: auto;" />
       <br />
-      <p>Illustration of the cross-domain diffusion pipeline for time step <i>t</i>. Initially, the pipeline generates a latent
+      <p>Illustration of the cross-domain diffusion pipeline for time step <i>t</i>. Initially, the pipeline generates a
+        latent
         code representing the source domain, which is subsequently used in the target domain generation to ensure detail
         preservation. During the generation phase, a preserved mask can be applied to maintain non-facial regions or to
         modify specific components.</p>
@@ -246,7 +247,8 @@ <h3 class="title is-4">B-4. Text Modification</h3>
         <img src="static/images/text_modification.svg" , alt="text modification"
           style=" display: block; margin-left: auto; margin-right: auto;" />
         <br />
-        <p>Text modification for non-makeup (<strong>top</strong>) and makeup (<strong>bottom</strong>) images. The images on the left
+        <p>Text modification for non-makeup (<strong>top</strong>) and makeup (<strong>bottom</strong>) images. The
+          images on the left
           modify the entire facial region, while those on the right demonstrate modification with a brush mask.</p>
       </div>
     </div>
@@ -258,7 +260,8 @@ <h2 class="title is-3">🗃️ C. MT-Text Dataset</h2>
       <p>We enhance the MT dataset <a href="#cite-1">[1]</a> with textual annotations. Initial descriptions of makeup
         for
         eyes, face, and lips were generated using GPT-4 Vision, followed by manual verification to
-        correct inaccuracies. Users can get the dataset from <a href="https://github.com/basiclab/MAD/blob/main/data/mt_text_anno.json" target="_blank">here</a>. </p><br />
+        correct inaccuracies. Users can get the dataset from <a
+          href="https://github.com/basiclab/MAD/blob/main/data/mt_text_anno.json" target="_blank">here</a>. </p><br />
       <div class="content is-centered has-text-centered">
         <img src="static/images/text-example.svg" , alt="text annotation"
           style=" display: block; margin-left: auto; margin-right: auto;" /><br />
@@ -282,9 +285,12 @@ <h2 class="title">Reference</h2>
   <section class="section" id="BibTeX">
     <div class="container is-max-desktop content">
       <h2 class="title">BibTeX</h2>
-      <pre><code>
-            BobTex
-        </code></pre>
+      <pre><code>@article{ruan2025mad,
+  title={MAD: Makeup All-in-One with Cross-Domain Diffusion Model},
+  author={Ruan, Bo-Kai and Shuai, Hong-Han},
+  journal={arXiv preprint arXiv:2504.02545},
+  year={2025}
+}</code></pre>
     </div>
   </section>