Add pipeline tag, library name, and link to paper/code

README.md

@@ -1,42 +1,49 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+language:
+- en
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
-
 <div align="center">
 
-<h1> R1-Router: Learning to Route Queries across Knowledge Bases for Step-wise Retrieval-Augmented Reasoning </h1>
-
+<h1> MoRE: Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation (R1-Router) </h1>
 
 <h5 align="center"> 
 
-<a href='https://arxiv.org/abs/2505.22095'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
-<a href='https://huggingface.co/hmhm1229/R1-Router'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue'>
-<a href='https://huggingface.co/hmhm1229/R1-Router-3B'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue'>
+<a href='https://huggingface.co/papers/2505.22095'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
+<a href='https://github.com/OpenBMB/R1-Router'><img src='https://img.shields.io/badge/Code-GitHub-black'></a>
+<a href='https://huggingface.co/hmhm1229/R1-Router'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue'></a>
+<a href='https://huggingface.co/hmhm1229/R1-Router-3B'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue'></a>
 
 Chunyi Peng<sup>1,3</sup>,
 Zhipeng Xu<sup>1</sup>,
 Zhenghao Liu<sup>1</sup>,
 Yishan Li<sup>3</sup>,
 Yukun Yan<sup>2</sup>,
+Shuo Wang<sup>2</sup>,
 Zhiyuan Liu<sup>2</sup>,
-Yu Gu<sup>1</sup>
-Minghe Yu<sup>1</sup>
-Ge Yu<sup>1</sup>
+Yu Gu<sup>1</sup>,
+Minghe Yu<sup>1</sup>,
+Ge Yu<sup>1</sup>,
 Maosong Sun<sup>2</sup>
 
-<sup>1</sup>Northeastern University, <sup>2</sup>Tsinghua University, <sup>3</sup>ModleBest Inc.
+<sup>1</sup>Northeastern University, <sup>2</sup>Tsinghua University, <sup>3</sup>ModelBest Inc.
 
 <h5 align="center"> If you find this project useful, please give us a star🌟.
 </h5>
 </div>
 
+**MoRE (Mixture-of-Retrieval Experts)** is a novel framework that enables Multimodal Large Language Models (MLLMs) to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation. It dynamically determines which expert to engage with based on the evolving reasoning state.
+
+This repository contains the **R1-Router** (7B version), which serves as the controller for routing queries across knowledge bases using **Stepwise Group Relative Policy Optimization (Step-GRPO)**.
+
 ## News
-8.22 We upload [R1-Router-3B](https://huggingface.co/hmhm1229/R1-Router-3B).
+- **2026.04.03**: Our work is accepted by SIGIR2026 🎉🎉🎉!
+- **2025.08.22**: We upload [MoRE-3B](https://huggingface.co/hmhm1229/R1-Router-3B).
 
 ## Environment
 For training, answer generation, and evaluation processes:
@@ -60,12 +67,12 @@ conda activate retriever
 wikiextractor enwiki-20241020-pages-articles-multistream.xml.bz2 -o wiki_extracted
 python wiki_preprocess.py
 ```
-For the image corpus, you can directly download [M-BEIR](https://huggingface.co/datasets/TIGER-Lab/M-BEIR). To embed and index it you can follow the [repository](https://github.com/TIGER-AI-Lab/UniIR)
+For the image corpus, you can directly download [M-BEIR](https://huggingface.co/datasets/TIGER-Lab/M-BEIR). To embed and index it you can follow the [repository](https://github.com/TIGER-AI-Lab/UniIR).
 
 For the table corpus, you can download, embed and index Open-WikiTable following the [repository](https://github.com/sean0042/Open_WikiTable), or you can download directly the one we have already preprocessed from [here](https://huggingface.co/hmhm1229/table-retriever). 
 
 ## Retrievers Preparation
-For the Text-Image Retriever, you can directly download [UniIR](https://huggingface.co/TIGER-Lab/UniIR)
+For the Text-Image Retriever, you can directly download [UniIR](https://huggingface.co/TIGER-Lab/UniIR).
 
 For the Table Retriever, you can train it with the help of [repository](https://github.com/sean0042/Open_WikiTable), or you can download it directly from [here](https://huggingface.co/hmhm1229/table-retriever). 
 
@@ -76,9 +83,10 @@ We have prepared all the text datasets in `./datasets`, for images you need to d
 - `WebQA:` WebQA images can be downloaded from [Google Drive](https://drive.google.com/drive/folders/19ApkbD5w0I5sV1IeQ9EofJRyAjKnA7tb)
 
 ## Training
-If you do not want to train the model, you can download [R1-Router](https://huggingface.co/hmhm1229/R1-Router) and skip this section to [Evaluation](#evaluation)
+If you do not want to train the model, you can download [R1-Router](https://huggingface.co/hmhm1229/R1-Router) and skip this section to [Evaluation](#evaluation).
+
 ### Data Synthesis
-If you want to use the ready-to-use synthetic data directly, you can skip this section to [Step-GRPO Training](#step-grpo-training)
+If you want to use the ready-to-use synthetic data directly, you can skip this section to [Step-GRPO Training](#step-grpo-training).
 
 First, we need to synthesis the data step by step:
 ```bash
@@ -112,11 +120,11 @@ Our work is built on the following codebases, and we are deeply grateful for the
 
 ## Citation
 We appreciate your citations if you find our paper related and useful to your research!
-```
-@article{peng2025r1,
-  title={Learning to Route Queries across Knowledge Bases for Step-wise Retrieval-Augmented Reasoning},
-  author={Peng, Chunyi and Xu, Zhipeng and Liu, Zhenghao and Li, Yishan and Yan, Yukun and Wang, Shuo and Liu, Zhiyuan and Gu, Yu and Yu, Minghe and Yu, Ge and Sun, Maosong},
-  year={2025}
+```bibtex
+@article{peng2025mixture,
+  title={Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation},
+  author={Peng, Chunyi and Xu, Zhipeng and Liu, Zhenghao and Li, Yishan and Yan, Yukun and Wang, Shuo and Liu, Zhiyuan and Gu, Yu and Minghe Yu and Ge Yu and Maosong Sun},
+  year={2025},
   url={https://arxiv.org/abs/2505.22095}, 
 }
 ```
@@ -125,4 +133,4 @@ We appreciate your citations if you find our paper related and useful to your re
 If you have questions, suggestions, and bug reports, please email us, we will try our best to help you.
 ```
 hm.cypeng@gmail.com
-```
+```