optimize for mobile

multimodal-interpretability · Apr 23, 2024 · 64c4b1a · 64c4b1a
1 parent b837b81
commit 64c4b1a
Showing 1 changed file with 17 additions and 3 deletions.
diff --git a/docs/index.html b/docs/index.html
@@ -49,6 +49,7 @@
       .title-text {  
 	font-size: 2rem;
       }
+
     } 
   </style>
 </head>
@@ -315,12 +316,25 @@ <h2 class="title is-3">Validating MAIA explanations</h2>
         <div style="border-style: solid; border-width: 1px; border-color: darkgray; padding: 20px; text-align: justify;">
             <p><h3 class="title is-4">Synthetic systems for evaluating automated interpretability methods</h3></p>
             <p>The synthetic neurons used to evaluate MAIA are part of a broader effort to construct a testbed of systems with known ground-truth structure that mimic subcomponents of trained networks. Automated Interpretability Agents interactively probe these systems to generate descriptions of their behavior, which are then automatically evaluated. For more details on our FIND (Function Interpretation and Description) benchmark and to download additional test sytems in non-visual domains, see our previous work:</p>
-            <div style="display: flex; flex-direction: row; align-items: center; padding-top: 20px;"> <div style="flex: 0 0 200px; margin-right: 20px;"> <img src="./static/figures/FIND.gif" alt="FIND" style="width: 100%; height: auto;"> </div> <div style="flex: 1;"> <p style="font-weight: bold; font-size: 1.25rem; margin-bottom: 0.5rem;">FIND: A Function Description Benchmark for Evaluating Interpretability Methods</p> <p>Sarah Schwettmann*, Tamar Rott Shaham*, Joanna Materzynska, Neil Chowdhury, Shuang Li, Jacob Andreas, David Bau, Antonio Torralba. NeurIPS 2023.</p> <p> <a href="https://arxiv.org/abs/2309.03886" target="_blank" style="margin-right: 10px;">Paper</a> <a href="https://github.com/multimodal-interpretability/FIND" target="_blank" style="margin-right: 10px;">Dataset</a> <a href="https://multimodal-interpretability.csail.mit.edu/FIND-benchmark/" target="_blank" style="margin-right: 10px;">Project Page</a> <a href="https://news.mit.edu/2024/ai-agents-help-explain-other-ai-systems-0103" target="_blank">News</a> </p> </div> </div>
-	</div>
+            <div class="content image-text-container" style="display: flex; align-items: center; padding-top: 20px;">
+                <div style="flex: 0 0 200px; margin-right: 20px;">
+                    <img src="./static/figures/FIND.gif" alt="FIND" style="width: 100%; height: auto;">
+                </div>
+                <div style="flex: 1;">
+                    <p style="font-weight: bold; font-size: 1.25rem; margin-bottom: 0.5rem;">FIND: A Function Description Benchmark for Evaluating Interpretability Methods</p>
+                    <p>Sarah Schwettmann*, Tamar Rott Shaham*, Joanna Materzynska, Neil Chowdhury, Shuang Li, Jacob Andreas, David Bau, Antonio Torralba. NeurIPS 2023.</p>
+                    <p>
+                        <a href="https://arxiv.org/abs/2309.03886" target="_blank" style="margin-right: 10px;">Paper</a>
+                        <a href="https://github.com/multimodal-interpretability/FIND" target="_blank" style="margin-right: 10px;">Dataset</a>
+                        <a href="https://multimodal-interpretability.csail.mit.edu/FIND-benchmark/" target="_blank" style="margin-right: 10px;">Project Page</a>
+                        <a href="https://news.mit.edu/2024/ai-agents-help-explain-other-ai-systems-0103" target="_blank">News</a>
+                    </p>
+                </div>
+            </div>
+        </div>
     </div>
 </section>
 
-
 
 <section class="section" id="BibTeX">
   <div class="container is-max-desktop content">