changes

Author: Subham

index.html

@@ -15,12 +15,12 @@
 
 
   <meta name="twitter:title" content="The Diffusion Duality">
-  <meta name="twitter:description" content="TWITTER BANNER DESCRIPTION META TAG">
+  <meta name="twitter:description" content="Unlocking Few-Step Generation in Discrete Diffusion Language Models">
   <!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X600-->
   <meta name="twitter:image" content="static/images/duo_schematic.png">
   <meta name="twitter:card" content="summary_large_image">
   <!-- Keywords for your paper to be indexed by-->
-  <meta name="keywords" content="The Diffusion Duality DUO">
+  <meta name="keywords" content="The Diffusion Duality DUO Diffusion Language Models">
   <meta name="viewport" content="width=device-width, initial-scale=1">
 
 
@@ -90,7 +90,7 @@ <h1 class="title is-1 publication-title">The Diffusion Duality</h1>
 
                         <!-- ArXiv abstract Link -->
                         <span class="link-block">
-                          <a href="https://openreview.net/forum?id=CB0Ub2yXjC" target="_blank"
+                          <a href="https://arxiv.org/abs/2506.10892v1" target="_blank"
                           class="external-link button is-normal is-rounded is-dark">
                           <span class="icon">
                             <i class="ai ai-arxiv"></i>
@@ -163,21 +163,15 @@ <h1 class="title is-1 publication-title">The Diffusion Duality</h1>
   <div class="container is-max-desktop">
     <div class="hero-body">
       <div style="text-align: center;">
-        <img src="static/images/duo_schematic.png" alt="MY ALT TEXT" style="width: 65%; height: auto;"/>
+        <img src="static/images/duo_schematic_graphical.png" alt="MY ALT TEXT" style="width: 65%; height: auto;"/>
       </div>
       <h4 class="subtitle has-text-centered">
         An illustration of uniform state discrete diffusion (top) and
         the underlying Gaussian diffusion (bottom). While both are separate Markov processes,
         applying \(\texttt{arg max}\) maps Gaussian latents \(\mathbf{w}_t \in \mathbb{R}^n\) to discrete latents
         \(\mathbf{z}_t \in \mathcal{V}\), transforming their marginals from
-        \(\tilde{q}_t(.|\mathbf{x}; \tilde{\alpha}_t)\)
-        <!-- ~\Eqn{eqn:gaussian_marginal} -->
-        to \(q_t(.|\mathbf{x}; \mathcal{T}(\tilde{\alpha}_t))\)
-        <!-- ~\Eqn{eqn:discrete_marginal} -->
-        and adjusting diffusion parameters from \(\tilde{\alpha}_t\)
-        to \(\alpha_t = \mathcal{T}(\tilde{\alpha}_t)\)
-        <!-- ~\Eqn{eqn:coefficient_relation} -->
-        .
+         \(K\)-dimensional Gaussian distribution to \(K\)-dimensional categorical distribution and adjusting diffusion parameters from \(\tilde{\alpha}_t\)
+        to \(\alpha_t = \mathcal{T}(\tilde{\alpha}_t)\).
         <!-- The ELBOs of both processes are related by \Eqn{eqn:elbo_inequality}. -->
       </h4>
       <!-- <img src="static/images/output.gif" width="100%" alt="A descriptive text for the GIF" > -->
@@ -323,10 +317,14 @@ <h2 class="title">BibTeX</h2>
       <button onclick="copyBibTeX()" style="position: absolute; top: 10px; right: 10px; z-index: 1;">
         Copy
       </button>
-      <pre><code id="bibtex-code">@inproceedings{sahoo2025diffusion,
-  title={The Diffusion Duality},
-  author={Sahoo, Subham Sekhar and Deschenaux, Justin and Gokaslan, Aaron and Wang, Guanghan and Chiu, Justin T and Kuleshov, Volodymyr},
-  booktitle={ICLR 2025 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy}
+      <pre><code id="bibtex-code">@misc{sahoo2025diffusionduality,
+  title={The Diffusion Duality}, 
+  author={Subham Sekhar Sahoo and Justin Deschenaux and Aaron Gokaslan and Guanghan Wang and Justin Chiu and Volodymyr Kuleshov},
+  year={2025},
+  eprint={2506.10892},
+  archivePrefix={arXiv},
+  primaryClass={cs.LG},
+  url={https://arxiv.org/abs/2506.10892}, 
 }</code></pre>
     </div>
   </div>