diff --git a/content/CSE5519/CSE5519_B3.md b/content/CSE5519/CSE5519_B3.md
index aba47b0..3210880 100644
--- a/content/CSE5519/CSE5519_B3.md
+++ b/content/CSE5519/CSE5519_B3.md
@@ -1,2 +1,13 @@
 # CSE5519 Advances in Computer Vision (Topic B: 2023: Vision-Language Models)
 
+## InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
+
+[link to paper](https://arxiv.org/pdf/2305.06500)
+
+> [!TIP]
+>
+> This paper introduces InstructBLIP, a framework for a vision-language model that aligns with text instructions.
+>
+> It consists of three submodules: the BLIP-2 model with an image decoder, an LLM, and a query Transformer (Q-former) to bridge the two.
+>
+> From qualitative results, we can see some hints that the model is following the text instructions, but I wonder if this framework could also bring to the image editing and generation tasks? What might be the difficulties in migrating this framework to context-awarded image generation?
\ No newline at end of file
diff --git a/content/CSE5519/CSE5519_H3.md b/content/CSE5519/CSE5519_H3.md
index 3416c63..97bd037 100644
--- a/content/CSE5519/CSE5519_H3.md
+++ b/content/CSE5519/CSE5519_H3.md
@@ -1,2 +1,13 @@
 # CSE5519 Advances in Computer Vision (Topic H: 2023: Safety, Robustness, and Evaluation of CV Models)
 
+## How to backdoor diffusion models
+
+[link to paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Chou_How_to_Backdoor_Diffusion_Models_CVPR_2023_paper.pdf )
+
+> [!TIP]
+>
+> This is an interesting paper showing that it is possible to backdoor a diffusion model with high utility and high specificity at a low cost compared to per-training.
+>
+> I wonder how this technique could possibly be used for AI watermarking and reliably detected with other AI operations?
+>
+> And there are many metrics and loss functions used in this paper, I wonder what objectives they are trying to optimize, and looking for more clarification on the presentation.
\ No newline at end of file