Update README.md

README.md

@@ -33,54 +33,16 @@ Building on these insights, we introduce U-MARVEL (Universal Multimodal Retrieva
 
 - [U-MARVEL-Qwen2VL-7B-Instruct](https://huggingface.co/TencentBAC/U-MARVEL-Qwen2VL-7B-Instruct) 🤗
 - [U-MARVEL-Qwen3VL-4B-Instruct](https://huggingface.co/TencentBAC/U-MARVEL-Qwen3VL-4B-Instruct) 🤗
-- Inference code available at: [U-MARVEL-inference](https://github.com/chaxjli/U-MARVEL)
-## Requirements
+- Code available at: [U-MARVEL](https://github.com/chaxjli/U-MARVEL)
+## 🚀 Demo
 
-To install requirements:
-
-```setup
-pip install -r requirements.txt
-```
-
-### Data Preparation
-
-Download Qwen2-VL-7B and place it in `./checkpoints/hf_models/Qwen2-VL-7B-Instruct`
-
-Download Qwen3-VL-4B and place it in `./checkpoints/hf_models/Qwen3-VL-4B-Instruct`
-
-For NLI dataset, please refer to [link](https://huggingface.co/datasets/princeton-nlp/datasets-for-simcse)
-
-For multimodal instruction tuning datset, please refer to [M-BEIR](https://huggingface.co/datasets/TIGER-Lab/M-BEIR)
-
-After downloading all of them, organize the data as follows in `./data`
-
-```
-├── data    
-│    ├── M-BEIR
-│    ├── nli_for_simcse.csv
-│    ├── rerank_data_for_training
-│    ├── flickr
-│    ├── coco
-│    ├── sharegpt4v
-│    ├── Urban1K
-│    ├── circo
-│    ├── genecis
-│    ├── vist
-│    ├── visdial
-│    ├── ccneg
-│    ├── sugar-crepe
-│    ├── MSVD
-│    └── msrvtt
-```
-
-## Evaluation
-
-To evaluate our model on M-BEIR, run:
+To get started, first create a virtual environment and install the required dependencies:
 
 ```bash
-python scripts/vtools_eval_mbeir_model.py  # Evaluate locally  
-sh scripts/eval_mbeir_global.sh            # Evaluate globally  
-sh scripts/eval_zeroshot.sh                # Evaluate zero-shot
+conda create -n u-marvel python=3.9 -y
+conda activate u-marvel
+pip install -r requirements_qwen2_vl.txt
+python demo.py
 ```
 
 ## Model Performance
@@ -104,10 +66,10 @@ Many thanks to the code bases from **[LamRA](https://github.com/Code-kunkun/LamR
 ## Citation
 If you use this code for your research or project, please cite:
 ```latex
-@article{li2025umarvel,
-  title={U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs},
-  author={Li, Xiaojie and Li, Chu and Chen, Shi-Zhe and Chen, Xi},
-  journal={arXiv preprint arXiv:2507.14902},
-  year={2025}
+@inproceedings{li2026umarvel,
+title={U-{MARVEL}: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with {MLLM}s},
+author={Xiaojie Li and Chu Li and Shi-Zhe Chen and Xi Chen},
+booktitle={The Fourteenth International Conference on Learning Representations},
+year={2026}
 }
 ```