Update README.md

README.md

@@ -7,7 +7,7 @@ pipeline_tag: question-answering
 
 # Code-as-World-VL-4B
 
-Code-as-World-VL-4B is a vision-language model fine-tuned for physical
+Code-as-World-VL-4B (https://arxiv.org/abs/2608.27549) is a vision-language model fine-tuned for physical
 understanding and quantitative reasoning over videos.
 
 ## Model details
@@ -47,3 +47,5 @@ This checkpoint is released under the Apache License 2.0. It is derived from
 [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B); users must also comply
 with the terms applicable to the base model and their input data.
 
+## Citation
+