diff --git a/README.md b/README.md
index fb2ab9ff..ac10784c 100644
--- a/README.md
+++ b/README.md
@@ -128,7 +128,7 @@ If you have any questions, please contact zmliu@mit.edu
 ## Author's note
 I would like to thank everyone who's interested in KANs. When I designed KANs and wrote codes, I have math & physics examples (which are quite small scale!) in mind, so did not consider much optimization in efficiency or reusability. It's so honored to receive this unwarranted attention, which is way beyond my expectation. So I accept any criticism from people complaning about the efficiency and resuability of the codes, my apology. My only hope is that you find `model.plot()` fun to play with :).
 
-For users who are interested in scientific discoveries and scientific computing (the orginal users intended for), I'm happy to hear your applications and collaborate. This repo will continue remaining mostly for this purpose, probably without signifiant updates for efficiency. In fact, there are already implmentations like [efficientkan](https://github.com/Blealtan/efficient-kan) or [fouierkan](https://github.com/GistNoesis/FourierKAN/) that look promising for improving efficiency.
+For users who are interested in scientific discoveries and scientific computing (the orginal users intended for), I'm happy to hear your applications and collaborate. This repo will continue remaining mostly for this purpose, probably without signifiant updates for efficiency. In fact, there are already implementations like [efficientkan](https://github.com/Blealtan/efficient-kan) or [fouierkan](https://github.com/GistNoesis/FourierKAN/) that look promising for improving efficiency.
 
 For users who are machine learning focus, I have to be honest that KANs are likely not a simple plug-in that can be used out-of-the box (yet). Hyperparameters need tuning, and more tricks special to your applications should be introduced. For example, [GraphKAN](https://github.com/WillHua127/GraphKAN-Graph-Kolmogorov-Arnold-Networks) suggests that KANs should better be used in latent space (need embedding and unembedding linear layers after inputs and before outputs). [KANRL](https://github.com/riiswa/kanrl) suggests that some trainable parameters should better be fixed in reinforcement learning to increase training stability.