Add paper abstract and BibTeX citation

This PR improves the model card for IC-Custom by adding the paper's abstract and a BibTeX citation.

The abstract provides a comprehensive overview of the model's purpose, methodology, and results, making the model card more informative. The BibTeX citation ensures that researchers can easily and correctly cite the associated paper.

No `library_name` was added to the metadata as there was no explicit evidence from the provided `config.json` or the (unavailable) GitHub README to confirm compatibility with a specific library, adhering to the guidelines. The existing arXiv paper link in the badges was kept as per instructions, which state not to replace it with a Hugging Face Papers link if an arXiv link is already present. Sample usage was not included as the GitHub README content, which would be the source of evidence, could not be fetched.

README.md

@@ -1,17 +1,16 @@
 ---
+base_model:
+- black-forest-labs/FLUX.1-Fill-dev
+language:
+- en
 license: other
 license_name: community-license-agreement
 license_link: LICENSE
-language:
-- en
-base_model:
-- black-forest-labs/FLUX.1-Fill-dev
 pipeline_tag: image-to-image
 tags:
 - image customization
 ---
 
-
 <div align="center">
   <a href="https://github.com/TencentARC/IC-Custom">
     <img src='https://github.com/TencentARC/IC-Custom/blob/main/assets/IC-Custom-logo.png?raw=true' width='120px'>
@@ -42,6 +41,9 @@ tags:
   </a>
 </div>
 
+### Abstract
+Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and position-free customization paradigms and lack a universal framework for diverse customization, limiting their applications across various scenarios. To overcome these limitations, we propose IC-Custom, a unified framework that seamlessly integrates position-aware and position-free image customization through in-context learning. IC-Custom concatenates reference images with target images to a polyptych, leveraging DiT's multi-modal attention mechanism for fine-grained token-level interactions. We introduce the In-context Multi-Modal Attention (ICMA) mechanism with learnable task-oriented register tokens and boundary-aware positional embeddings to enable the model to correctly handle different task types and distinguish various inputs in polyptych configurations. To bridge the data gap, we carefully curated a high-quality dataset of 12k identity-consistent samples with 8k from real-world sources and 4k from high-quality synthetic data, avoiding the overly glossy and over-saturated synthetic appearance. IC-Custom supports various industrial applications, including try-on, accessory placement, furniture arrangement, and creative IP customization. Extensive evaluations on our proposed ProductBench and the publicly available DreamBench demonstrate that IC-Custom significantly outperforms community workflows, closed-source models, and state-of-the-art open-source approaches. IC-Custom achieves approximately 73% higher human preference across identity consistency, harmonicity, and text alignment metrics, while training only 0.4% of the original model parameters.
+
 <p align="center">
   IC-Custom is designed for diverse image customization scenarios, including:
 </p>
@@ -52,7 +54,14 @@ tags:
 - **Position-free**: Input a reference image and a target description to generate a new image with the reference image's ID  
   *Examples*: IP customization, character creation.
 
-
 ### Citation
 
-If you find IC-Custom useful, please consider giving it a ⭐ on [GitHub](https://github.com/TencentARC/IC-Custom).
+```bibtex
+@article{li2025iccustom,
+  title={IC-Custom: Diverse Image Customization via In-Context Learning},
+  author={Li, Yaowei and Zhu, Yu and Wu, Xu and Liu, Bo and Li, Jia and Lu, Yong and Zhang, Song and Luo, Yujun},
+  journal={arXiv preprint arXiv:2507.01926},
+  year={2025},
+  url={https://arxiv.org/abs/2507.01926}
+}
+```