feat: add research field of machine unlearning of t2i

research_participate.html

@@ -92,6 +92,26 @@ <h4 class="header"># Machine Unlearning - Advisors: Jungseul Ok / Sangdon Park <
     </div>
 </li>
 
+  <li>
+    <div class="row" style="padding-top: 40px;">
+      <div class="col-sm-2" >
+          <img class="img-responsive img-header" src="img/reseach_participate/unlearning.png" alt=""  />
+      </div>
+      <div class="col-sm-10">
+          <h4 class="header"># Machine Unlearning in Text-to-Image Generative Models - Advisor: Dongwoo Kim, Mentor: Saemi Moon, Minjong Lee </h4>
+          <p class="normal-text">
+            Generative models have made significant advancements in producing high-quality images, but they also pose risks by potentially generating harmful, explicit, or privacy- and copyright-infringing content. To address these concerns, we aim to develop methods that allow models to “unlearn” problematic concepts, thereby enhancing the ethical and safe deployment of these models.
+          </p>
+          <span class="sub-text"> References </span>
+          <ol class="sub-text">
+              <li> Moon, Saemi, Seunghyuk Cho, and Dongwoo Kim. <a href="https://arxiv.org/abs/2205.15567">"Feature Unlearning for Pre-trained GANs and VAEs."</a> AAAI 2024</li>
+              <li> Kumari, Nupur, et al. <a href="https://arxiv.org/abs/2303.13516">"Ablating concepts in text-to-image diffusion models."</a> NuerIPS 2023. </li>
+              <li> Gandikota, Rohit, et al. <a href="https://arxiv.org/abs/2303.07345">"Erasing Concepts from Diffusion Models."</a> ICCV 2023.</li>
+          </ol>
+      </div>
+  </div>
+</li>
+
 <li>
   <div class="row" style="padding-top: 40px;">
     <div class="col-sm-2">