diff --git a/_posts/2024/05/2024-05-26-mini-seminar.md b/_posts/2024/05/2024-05-26-mini-seminar.md
index 01c88dd..0726fc1 100644
--- a/_posts/2024/05/2024-05-26-mini-seminar.md
+++ b/_posts/2024/05/2024-05-26-mini-seminar.md
@@ -36,16 +36,11 @@ imgUrl: /assets/source/image/blog/
 
 ## Motivation
 
-**Challenges with AI in Robotics for Traditional Approaches:**
- - Limited Adaptability 
-   - Struggle to adapt to new tasks or environments without reprogramming / retraining.
- - High Dependence on Human Intervention
-   - Require significant human effort for data labeling and feature extraction for training models.
- - Poor Generalization
-   - Lack the ability to generalize across different contexts and applications.
+**Challenges with Traditional AI in Robotic systems:**
+ - Traditional AI models are great at specific, well-defined tasks but they face challenges when dealing with unpredictable, real-world environments.
+ - The variability of real-world tasks makes it hard for AI to generalize effectively.
 
-**Proposed Research Topics**
- - **Leveraging Large Language Models (LLMs) to control robots as an embodied agent**:
+**Leveraging Large Language Models:**
 
 ```mermaid
 
@@ -76,13 +71,13 @@ graph LR;
 
 **Research Questions**
  - How can LLMs be effectively integrated into general-purpose robotic systems to improve the 
- interpretation of natural language instructions and multi-modal sensory data for enhanced task planning and action 
-   generation?
+ interpretation of natural language instructions and multi-modal sensory data for enhanced task planning and action generation?
  - What are the optimal strategies that allows LLMs to access and utilize domain-specific knowledge in real-time to improve the performance and adaptability of general-purpose robots?
  - How can we mitigate the risks of inaccurate or false information (hallucinations) generated by LLMs, such as mismatches between robots' actions and LLM-generated explanations, to enhance transparency and trust in human-robot interactions?
 
 ## Background
 
+3 processes in robotic system
 ```mermaid
 
 graph LR;
@@ -168,7 +163,7 @@ graph LR;
 
 ## Current Work
 
-LLM for Robotics Navigations using Eyesim simulator
+LLM for mobile robot navigations using Eyesim
 
 
 ![img]({{ page.imgUrl }}eyesimllm.png)