Upload README.md with huggingface_hub

README.md

@@ -30,6 +30,10 @@ datasets:
 
 **Paper:** [MemeLens: Multilingual Multitask VLMs for Memes](https://arxiv.org/abs/2601.12539)
 
+<p align="center">
+  <img src="assets/memelens_task_dataset.png" width="100%" alt="MemeLens Data Construction Overview">
+</p>
+
 ## Overview
 
 | | |
@@ -105,6 +109,10 @@ Acc = Accuracy, Ma = Macro-F1, W = Weighted-F1. Bold indicates best performance
 
 ## Supported Tasks
 
+<p align="center">
+  <img src="assets/Language_Task.png" width="60%" alt="Task and Language Distribution">
+</p>
+
 The model supports 20 meme understanding tasks across multiple categories:
 
 | Category | Tasks |