Improve model card: Add pipeline_tag, library_name, and update paper links

README.md

@@ -1,16 +1,19 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-7B-Instruct
+language:
+- en
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: hpsv3
 ---
+
 <div align="center">
 
 # 🎯 HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV 2025)
 
 [![Project Website](https://img.shields.io/badge/🌐-Project%20Website-deepgray)](https://mizzenai.github.io/HPSv3.project/)
-[![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)]()
+[![arXiv](https://img.shields.io/badge/arXiv-2508.03789-b31b1b.svg)](https://arxiv.org/abs/2508.03789)
 [![ICCV 2025](https://img.shields.io/badge/ICCV-2025-blue.svg)]()
 [![Code](https://img.shields.io/badge/Code-black?logo=github)](https://github.com/MizzenAI/HPSv3)
 [![Model](https://img.shields.io/badge/🤗-Model-yellow)](https://huggingface.co/MizzenAI/HPSv3)
@@ -37,7 +40,7 @@ base_model:
 
 ## 📖 Introduction
 
-This is the official implementation for the paper: [HPSv3: Towards Wide-Spectrum Human Preference Score]().
+This is the official implementation for the paper: [HPSv3: Towards Wide-Spectrum Human Preference Score](https://huggingface.co/papers/2508.03789).
 First, we introduce a VLM-based preference model **HPSv3**, trained on a "wide spectrum" preference dataset **HPDv3** with 1.08M text-image pairs and 1.17M annotated pairwise comparisons, covering both state-of-the-art and earlier generative models, as well as high- and low-quality real-world images. Second, we propose a novel reasoning approach for iterative image refinement, **CoHP(Chain-of-Human-Preference)**, which efficiently improves image quality without requiring additional training data.
 
 <p align="center">
@@ -293,8 +296,8 @@ COHP uses multiple state-of-the-art diffusion models for initial generation: **F
 1. **Multi-Model Generation**: Generates images using all supported models
 2. **Reward Scoring**: Evaluates each image using the specified reward model
 3. **Best Model Selection**: Chooses the model that produced the highest-scoring image
-4. **Iterative Refinement**: Performs 5 rounds of image-to-image generation to improve quality
-5. **Adaptive Strength**: Uses strength=0.8 for rounds 1-2, then 0.5 for rounds 3-5
+4. **Iterative Refinement**: Performs 4 rounds of image-to-image generation to improve quality
+5. **Adaptive Strength**: Uses strength=0.8 for rounds 1-2, then 0.5 for rounds 3-4
 
 ---
 
@@ -343,4 +346,4 @@ We would like to thank the [VideoAlign](https://github.com/KwaiVGI/VideoAlign) c
 
 For questions and support:
 - **Issues**: [GitHub Issues](https://github.com/MizzenAI/HPSv3/issues)
-- **Email**: xilanhua12138@sjtu.edu.cn & [email protected]
+- **Email**: yhshui@mizzen.ai & [email protected]