Update paper link and citation in model card

README.md

@@ -1,22 +1,22 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-VL-32B-Instruct
 datasets:
 - OpenGVLab/ScaleCUA-Data
 language:
 - en
+library_name: transformers
+license: apache-2.0
 metrics:
 - accuracy
-base_model:
-- Qwen/Qwen2.5-VL-32B-Instruct
 pipeline_tag: image-text-to-text
-library_name: transformers
 tags:
 - agent
 ---
 
 # SCALECUA: SCALING UP COMPUTER USE AGENTS WITH CROSS-PLATFORM DATA
 
-[\[📂 GitHub\]](https://github.com/OpenGVLab/ScaleCUA) [\[📜 Paper\]](https://github.com/OpenGVLab/ScaleCUA) [\[🚀 Quick Start\]](#model-loading)
+[\[📂 GitHub\]](https://github.com/OpenGVLab/ScaleCUA) [\[📜 Paper\]](https://huggingface.co/papers/2509.15221) [\[🚀 Quick Start\]](#model-loading)
 
 
 
@@ -120,19 +120,13 @@ messages = [
     {
       "role": "system",
       "content":[
-        {
-          "type": "text",
-          "text": SCALECUA_SYSTEM_PROMPT_GROUNDER,
-        }
+        {"type": "text", "text": SCALECUA_SYSTEM_PROMPT_GROUNDER,}
       ]
     },
     {
         "role": "user",
         "content": [
-            {
-                "type": "image",
-                "image": "/path/to/your/image",
-            },
+            {"type": "image", "image": "/path/to/your/image",},
             {"type": "text", "text": low_level_instruction},
         ],
     }
@@ -171,7 +165,7 @@ def parse_scalecua_grounder_response(response, image_width: int, image_height: i
     logger.info(f"Extracting coordinates from: {response}")
     match = re.search(r"\((\d+),\s*(\d+)\)", response)
     if not match:
-        pattern = r'\((?:x=)?([-+]?\d*\.\d+|\d+)(?:,\s*(?:y=)?([-+]?\d*\.\d+|\d+))?\)'
+        pattern = r'\((?:x=)?([-+]?\d*\.\d+|\d+)(?:,\s*(?:y=)?([-+]?\d*\\.\\d+|\\d+))?\)'
         match = re.search(pattern, response)
     x = int(float(match.group(1))  / resized_width * width)
     y = int(float(match.group(2)) / resized_height * height) if match.group(2) else None 
@@ -315,7 +309,8 @@ Previous operations:
 def format_history(history):
     if len(history) > 0:
         actions_history = [f"Step {i+1}: {low_level}" for i, low_level in enumerate(history)]
-        return "\n".join(actions_history) 
+        return "
+".join(actions_history) 
     else:
         return None
 
@@ -333,19 +328,13 @@ messages = [
     {
       "role": "system",
       "content":[
-        {
-          "type": "text",
-          "text": SCALECUA_SYSTEM_PROMPT_AGENT,
-        }
+        {"type": "text", "text": SCALECUA_SYSTEM_PROMPT_AGENT,}
       ]
     },
     {
         "role": "user",
         "content": [
-            {
-                "type": "image",
-                "image": "/path/to/your/image",
-            },
+            {"type": "image", "image": "/path/to/your/image",},
             {"type": "text", "text": user_prompt},
         ],
     }
@@ -382,7 +371,8 @@ def parse_response(response: str) -> Dict:
     if action_matches:
         for match in action_matches:
             # Split each match by newline and strip whitespace from each line
-            lines = [line.strip() for line in match.split('\n') if line.strip()]
+            lines = [line.strip() for line in match.split('
+') if line.strip()]
             actions.extend(lines)
     operation_match = re.search(r'<operation>\s*(.*?)\s*</operation>', response, re.DOTALL)
     operation = operation_match.group(1).strip() if operation_match else None
@@ -456,12 +446,12 @@ def parse_actions(self, actions):
 
         else:
             if "=" in args_str:
-                for arg in re.finditer(r"(\w+)=\[([^\]]+)\]", args_str):
+                for arg in re.finditer(r"(\w+)=\\[([^\\]]+)\\]", args_str):
                     param = arg.group(1)
                     list_str = arg.group(2)
                     
                     list_items = []
-                    for item in re.finditer(r"'([^']*)'|\"([^\"]*)\"|([^,\]]+)", list_str):
+                    for item in re.finditer(r"'([^']*)'|\"([^\"]*)\"|([^,\\]]+)", list_str):
                         val = (item.group(1) or item.group(2) or item.group(3)).strip()
                         if val:
                             list_items.append(val.strip('"\'')) 
@@ -529,9 +519,11 @@ If you find our project useful in your research, please consider citing:
 
 ```bibtex
 @article{liu2025scalecua,
-  title = {ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data},
-  author = {Liu, Zhaoyang and Xie, Jingjing and Ding, Zichen and Li, Zehao and Yang, Bowen and Wu, Zhenyu and Wang, Xuehui and Sun, Qiushi and Liu, Shi and Wang, Weiyun and Ye, Shenglong and Li, Qingyun and Dong, Xuan and Yu, Yue and Lu, Chenyu and Mo, YunXiang and Yan, Yao and Tian, Zeyue and Zhang, Xiao and Huang, Yuan and Liu, Yiqian and Su, Weijie and Luo, Gen and Yue, Xiangyu and Qi, Biqing and Chen, Kai and Zhou, Bowen and Qiao, Yu and Chen, Qifeng and Wang, Wenhai},
-  year = {2025},
+  title        = {ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data},
+  author       = {Liu, Zhaoyang and Xie, Jingjing and Ding, Zichen and Li, Zehao and Yang, Bowen and Wu, Zhenyu and Wang, Xuehui and Sun, Qiushi and Liu, Shi and Wang, Weiyun and Ye, Shenglong and Li, Qingyun and Dong, Xuan and Yu, Yue and Lu, Chenyu and Mo, YunXiang and Yan, Yao and Tian, Zeyue and Zhang, Xiao and Huang, Yuan and Liu, Yiqian and Su, Weijie and Luo, Gen and Yue, Xiangyu and Qi, Biqing and Chen, Kai and Zhou, Bowen and Qiao, Yu and Chen, Qifeng and Wang, Wenhai},
+  journal      = {arXiv preprint arXiv:2509.15221},
+  year         = {2025},
+  note         = {Preprint},
   url = {https://github.com/OpenGVLab/ScaleCUA}
 }
 ```