Image-to-Text
Transformers
English
qwen2_vl
ziyjiang commited on
Commit
395632b
·
verified ·
1 Parent(s): 054f040

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -7,6 +7,10 @@
7
  - **\[2025.07\]** Release [tech report](https://arxiv.org/abs/2507.04590).
8
  - **\[2025.05\]** Initial release of MMEB-V2/VLM2Vec-V2.
9
 
 
 
 
 
10
  ## How to use VLM2Vec
11
  We have provided demo example in our [Github](https://github.com/TIGER-AI-Lab/VLM2Vec/tree/main/experiments/examples/qwen2vl).
12
 
 
7
  - **\[2025.07\]** Release [tech report](https://arxiv.org/abs/2507.04590).
8
  - **\[2025.05\]** Initial release of MMEB-V2/VLM2Vec-V2.
9
 
10
+ ### Experimental Results
11
+ Our model can outperform the existing baselines by a huge margin.
12
+ <img width="900" alt="abs" src="https://github.com/TIGER-AI-Lab/VLM2Vec/blob/gh-pages/static/images/vlm2vec_v2_result.png">
13
+
14
  ## How to use VLM2Vec
15
  We have provided demo example in our [Github](https://github.com/TIGER-AI-Lab/VLM2Vec/tree/main/experiments/examples/qwen2vl).
16