From 71ada8d4986f2801a70a4c8cced1b1fe03d2dde5 Mon Sep 17 00:00:00 2001
From: Trance-0 <60459821+Trance-0@users.noreply.github.com>
Date: Mon, 3 Nov 2025 23:56:22 -0600
Subject: [PATCH] sad

---
 content/CSE5519/CSE5519_B4.md | 15 +++++++++++++++
 package.json                  |  7 ++++---
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/content/CSE5519/CSE5519_B4.md b/content/CSE5519/CSE5519_B4.md
index e6037b4..74ad181 100644
--- a/content/CSE5519/CSE5519_B4.md
+++ b/content/CSE5519/CSE5519_B4.md
@@ -1,2 +1,17 @@
 # CSE5519 Advances in Computer Vision (Topic B: 2024: Vision-Language Models)
 
+## Improved Baselines with Visual Instruction Tuning (LLaVA-1.5)
+
+[link to the paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Liu_Improved_Baselines_with_Visual_Instruction_Tuning_CVPR_2024_paper.pdf)
+
+This paper shows that the visual instruction tuning can improve the performance of the vision-language model.
+
+### Novelty in LLaVA-1.5
+
+1. Scaling to high resolution images by dividing images into grids and maintaining the data efficiency.
+2. Compositional ability, (use long-form language reasoning together with shorter visual reasoning can improve the model's writing ability)
+3. Random downsampling will not degrade the performance.
+
+>[!TIP] 
+>
+> This paper shows that LLaVA-1.5 obeys the scaling law and splitting the high resolution images into grids to maintain the data efficiency. I wonder why this method is not applicable to multi-image understanding tasks? Why we cannot assign index embeddings to each image and push the image sets to the model for better understanding?
\ No newline at end of file
diff --git a/package.json b/package.json
index d741347..6714dcb 100644
--- a/package.json
+++ b/package.json
@@ -15,14 +15,15 @@
     "@vercel/analytics": "^1.5.0",
     "@vercel/speed-insights": "^1.2.0",
     "cross-env": "^7.0.3",
+    "eslint-config-next": "^16.0.1",
     "katex": "^0.16.22",
-    "next": "^15.5.2",
+    "next": "^16.0.1",
     "next-sitemap": "^4.2.3",
     "nextra": "^4.2.17",
     "nextra-theme-docs": "^4.2.17",
     "pagefind": "^1.4.0",
-    "react": "^19.1.0",
-    "react-dom": "^19.1.0"
+    "react": "^19.2.0",
+    "react-dom": "^19.2.0"
   },
   "devDependencies": {
     "@types/node": "24.0.10",