diff --git a/docs/source/multitask_dit.mdx b/docs/source/multitask_dit.mdx
new file mode 100644
index 000000000..e69de29bb
diff --git a/src/lerobot/policies/multi_task_dit/README.md b/src/lerobot/policies/multi_task_dit/README.md
index 1628a7c12..3ede6f174 100644
--- a/src/lerobot/policies/multi_task_dit/README.md
+++ b/src/lerobot/policies/multi_task_dit/README.md
@@ -9,7 +9,7 @@ If you use this work, please cite the following works:
   author = {Bryson Jones},
   title = {Dissecting and Open-Sourcing Multitask Diffusion Transformer Policy},
   year = {2025},
-  url = {https://brysonkjones.substack.com/p/dissecting-multitask-diffusion-transformer-policy},
+  url = {https://brysonkjones.substack.com/p/dissecting-and-open-sourcing-multitask-diffusion-transformer-policy},
   note = {Blog post}
 }
 ```
diff --git a/src/lerobot/policies/multi_task_dit/modeling_multi_task_dit.py b/src/lerobot/policies/multi_task_dit/modeling_multi_task_dit.py
index 77adb5d73..0eeaa3025 100644
--- a/src/lerobot/policies/multi_task_dit/modeling_multi_task_dit.py
+++ b/src/lerobot/policies/multi_task_dit/modeling_multi_task_dit.py
@@ -18,6 +18,11 @@
 
 Transformer-based diffusion policy for multi-task robot learning with text and vision conditioning.
 Supports both diffusion and flow matching objectives for action generation.
+
+References:
+- https://arxiv.org/abs/2507.05331
+- https://brysonkjones.substack.com/p/dissecting-and-open-sourcing-multitask-diffusion-transformer-policy
+- https://brysonkjones.substack.com/p/dissecting-multitask-diffusion-transformer-policy
 """
 
 from collections import deque