Improve model card: Add pipeline tag, library name, paper, and project page links

README.md

@@ -1,7 +1,9 @@
 ---
-language: 
-  - en
-  - zh
+base_model: Qwen/Qwen3-VL-4B-Instruct
+language:
+- en
+- zh
+license: apache-2.0
 tags:
 - gui-agent
 - phone-use agent
@@ -10,10 +12,14 @@ tags:
 - android
 - multimodal
 - gelab-zero
-license: apache-2.0
-base_model: Qwen/Qwen3-VL-4B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
+# GELab-Zero-4B-preview
+
+This model is part of the **GELab-Zero** project, which presents the **Step-GUI Technical Report** [[Paper](https://huggingface.co/papers/2512.15431)] [[Project Page](https://opengelab.github.io/)] [[Code](https://github.com/stepfun-ai/gelab-zero)].
+
 ## Model Details
 
 This model is part of the [**GELab-Zero**](https://github.com/stepfun-ai/gelab-zero) project, which aims to accelerate the innovation and application deployment of GUI Agents by providing:
@@ -92,5 +98,4 @@ If you find GELab-Zero-4B-preview useful for your research, please consider citi
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2512.02423}, 
 }
-
-```
+```