paper

Author: Ruotian-Peng

index.html

@@ -165,7 +165,7 @@ <h1 class="title is-1 publication-title is-bold">
         <br>
         <img src="static/images/teaser.png" alt="algebraic reasoning" class="center" style="width:95%;height:auto;">
         <br>
-        <figcaption style="text-align:left;">Figure1: SimKO improves pass@K performance on math tasks (AIME24/25, AMC, MATH500, Minerva, Olympiadbench) and logic tasks (Synlogic, BBH) compared to GRPO, as shown in the plots (left and middle). The Figure1 on the right shows the k-th highest candidate probabilities averaged over the dataset. The SimKO-trained model exhibits a less concentrated probability distribution compared to GRPO.</figcaption>
+        <figcaption style="text-align:left;">Figure1: SimKO improves pass@K performance on math tasks (AIME24/25, AMC, MATH500, Minerva, Olympiadbench) and logic tasks (Synlogic, BBH) compared to GRPO, as shown in the plots (left and middle). The figure on the right shows the k-th highest candidate probabilities averaged over the dataset. The SimKO-trained model exhibits a less concentrated probability distribution compared to GRPO.</figcaption>
         <br>
         <h2 class="title is-3">Abstract</h2>
         <div class="content has-text-justified">
@@ -359,7 +359,7 @@ <h1 class="title is-1 mmmu">Results</h1>
   <div class="container is-max-desktop content">
     <h2 class="title is-3 has-text-centered">BibTeX</h2>
     <pre><code>
-      @article{yu2025simko,
+      @article{peng2025simko,
         title={SimKO: Simple Pass@K Policy Optimization},
         author={Peng, Ruotian and Ren, Yi and Yu, Zhouliang and Liu, Weiyang and Wen, Yandong},
         journal={arXiv preprint arXiv:2510.14807},