.

README.md

@@ -1,16 +1,36 @@
 # GameNGen
 
-We present GameNGen, the first game engine powered entirely by a neural model
+**Diffusion Models Are Real-Time Game Engines**\
+Dani Valevski, Yaniv Leviathan, Moab Arar, Shlomi Fruchter\
+Paper: [https://arxiv.org/abs/2408.14837](https://arxiv.org/abs/2408.14837)
+
+## Abstract
+
+We present _GameNGen_, the first game engine powered entirely by a neural model
 that enables real-time interaction with a complex environment over long trajectories at high quality.
-GameNGen can interactively simulate the classic game DOOM at over 20 frames per second on a single
-TPU. GameNGen simulations do not suffer from accumulated deterioration even after long play sessions,
+_GameNGen_ can interactively simulate the classic game DOOM at over 20 frames per second on a single
+TPU. _GameNGen_ simulations do not suffer from accumulated deterioration even after long play sessions,
 achieving a PSNR of 29.4, comparable to lossy JPEG compression.
 Human raters are only slightly better than random chance at distinguishing short clips of the game
 from clips of the simulation.
-GameNGen is trained in two phases:
+_GameNGen_ is trained in two phases:
 (1) an RL-agent learns to play the game and the training sessions are recorded, and
 (2) a diffusion model is trained to produce the next frame, conditioned on the sequence of past frames and
 actions. Conditioning augmentations enable stable auto-regressive generation over long trajectories.
 
-## Acknowledgments
+## Citation
+
+```bibtex
+@misc{valevski2024diffusionmodelsrealtimegame,
+      title={Diffusion Models Are Real-Time Game Engines}, 
+      author={Dani Valevski and Yaniv Leviathan and Moab Arar and Shlomi Fruchter},
+      year={2024},
+      eprint={2408.14837},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2408.14837}, 
+}
+```
+
+### Acknowledgments
 This page was built using the [Academic Project Page Template](https://github.com/eliahuhorwitz/Academic-project-page-template) which was adopted from the [Nerfies](https://nerfies.github.io) project page.

index.html

@@ -84,10 +84,10 @@ <h1 class="title is-1 publication-title">Diffusion Models Are Real-Time Game Eng
               <span class="eql-cntrb"><small><br><sup>*</sup>Equal Contribution <sup>†</sup>Work done while at Google
                   Research</small></span>
             </div>
-            <!-- <div class="column has-text-centered">
+            <div class="column has-text-centered">
             <div class="publication-links">
               <span class="link-block">
-                <a href="https://arxiv.org/pdf/TODO.pdf" target="_blank"
+                <a href="https://arxiv.org/pdf/2408.14837" target="_blank"
                 class="external-link button is-normal is-rounded is-dark">
                   <span class="icon">
                     <i class="fas fa-file-pdf"></i>
@@ -96,7 +96,7 @@ <h1 class="title is-1 publication-title">Diffusion Models Are Real-Time Game Eng
                 </a>
               </span>
             </div>
-          </div> -->
+          </div>
           </div>
         </div>
       </div>
@@ -222,12 +222,20 @@ <h2 class="title is-3">Architecture</h2>
     </div>
   </section>
 
-  <!-- <section class="section" id="BibTeX">
+  <section class="section" id="BibTeX">
     <div class="container is-max-desktop content">
       <h2 class="title">BibTeX</h2>
-      <pre><code>@article{TODO once this is on arxiv}</code></pre>
+      <pre><code>@misc{valevski2024diffusionmodelsrealtimegame,
+        title={Diffusion Models Are Real-Time Game Engines}, 
+        author={Dani Valevski and Yaniv Leviathan and Moab Arar and Shlomi Fruchter},
+        year={2024},
+        eprint={2408.14837},
+        archivePrefix={arXiv},
+        primaryClass={cs.LG},
+        url={https://arxiv.org/abs/2408.14837}, 
+  }</code></pre>
     </div>
-  </section> -->
+  </section>
 
   <section class="section" id="Acknowledgements">
     <div class="container is-max-desktop content">