diff --git a/vision/notes.md b/vision/notes.md
new file mode 100644
index 0000000..4d311c5
--- /dev/null
+++ b/vision/notes.md
@@ -0,0 +1,25 @@
+ Visual options :
+ -- OD:
+ - object detction /w fine tuning: Yolo V5: https://learnopencv.com/custom-object-detection-training-using-yolov5/
+
+-- V-aware
+ - visual LLM: LLAVA : https://llava.hliu.cc/
+
+ -- BOTH detection and comprehention: 
+ -Phi
+ https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
+ https://github.com/microsoft/Phi-3CookBook
+
+- Lavva chat
+https://github.com/LLaVA-VL/LLaVA-Interactive-Demo?tab=readme-ov-file
+git clone https://github.com/LLaVA-VL/LLaVA-Interactive-Demo.git
+conda create -n llava_int -c conda-forge -c pytorch python=3.10.8 pytorch=2.0.1 -y
+conda activate llava_int
+cd LLaVA-Interactive-Demo
+pip install -r requirements.txt
+source setup.sh
+
+
+
+
+- decision making based on ENV, RL: https://github.com/OpenGenerativeAI/llm-colosseum
\ No newline at end of file