diff --git a/content/posts/math-2024/bib.bib b/content/posts/math-2024/bib.bib
index 7b2ff49..34ec730 100644
--- a/content/posts/math-2024/bib.bib
+++ b/content/posts/math-2024/bib.bib
@@ -428,9 +428,17 @@ @article{sen2024string
 }
 
 @inproceedings{bao2023all,
-  title={All are worth words: A vit backbone for diffusion models},
+  title={All are worth words: A ViT backbone for diffusion models},
   author={Bao, Fan and Nie, Shen and Xue, Kaiwen and Cao, Yue and Li, Chongxuan and Su, Hang and Zhu, Jun},
   booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
   pages={22669--22679},
   year={2023}
 }
+
+@article{mikula2023magnushammer,
+  title={Magnushammer: A transformer-based approach to premise selection},
+  author={Miku{\l}a, Maciej and Antoniak, Szymon and Tworkowski, Szymon and Jiang, Albert Qiaochu and Zhou, Jin Peng and Szegedy, Christian and Kuci{\'n}ski, {\L}ukasz and Mi{\l}o{\'s}, Piotr and Wu, Yuhuai},
+  journal={arXiv preprint arXiv:2303.04488},
+  year={2023}
+}
+
diff --git a/content/posts/math-2024/bib.json b/content/posts/math-2024/bib.json
index df0313f..6b7123f 100644
--- a/content/posts/math-2024/bib.json
+++ b/content/posts/math-2024/bib.json
@@ -1298,8 +1298,60 @@
       ]
     },
     "page": "22669-22679",
-    "title": "All are worth words: A vit backbone for diffusion models",
+    "title": "All are worth words: A ViT backbone for diffusion models",
     "title-short": "All are worth words",
     "type": "paper-conference"
+  },
+  {
+    "author": [
+      {
+        "family": "Mikuła",
+        "given": "Maciej"
+      },
+      {
+        "family": "Antoniak",
+        "given": "Szymon"
+      },
+      {
+        "family": "Tworkowski",
+        "given": "Szymon"
+      },
+      {
+        "family": "Jiang",
+        "given": "Albert Qiaochu"
+      },
+      {
+        "family": "Zhou",
+        "given": "Jin Peng"
+      },
+      {
+        "family": "Szegedy",
+        "given": "Christian"
+      },
+      {
+        "family": "Kuciński",
+        "given": "Łukasz"
+      },
+      {
+        "family": "Miłoś",
+        "given": "Piotr"
+      },
+      {
+        "family": "Wu",
+        "given": "Yuhuai"
+      }
+    ],
+    "container-title": "arXiv preprint arXiv:2303.04488",
+    "id": "mikula2023magnushammer",
+    "issued": {
+      "date-parts": [
+        [
+          2023
+        ]
+      ]
+    },
+    "title": "Magnushammer: A transformer-based approach to premise selection",
+    "title-short": "Magnushammer",
+    "type": "article-journal"
   }
 ]
diff --git a/content/posts/math-2024/index.md b/content/posts/math-2024/index.md
index 11c5359..d9aae27 100644
--- a/content/posts/math-2024/index.md
+++ b/content/posts/math-2024/index.md
@@ -225,6 +225,8 @@ I might need to follow on the latest development on the linear attention mechani
 
 I have almost no understanding of diffusion models, so I should read {{< cite "bao2023all" >}} and related papers.
 
+I should also read {{< cite "mikula2023magnushammer" >}} and related papers.
+
 ### Consciousness
 
 Lately I became aware of the work on mathematical models of consciousness, namely Integrated information theory {{< cite "albantakis2023integrated" >}} and The information theory of individuality {{< cite "krakauer2020information" >}}.