Improve model card: add paper links, authors, and usage instructions

README.md

@@ -1,5 +1,8 @@
 ---
+language:
+- en
 license: mit
+pipeline_tag: object-detection
 tags:
 - computer-vision
 - 3d-object-detection
@@ -11,27 +14,21 @@ tags:
 - opv2v
 - v2xset
 - dair-v2x
-language:
-- en
-pipeline_tag: object-detection
 ---
 
-# SiMO: Single-Modal-Operable Multimodal Collaborative Perception
+# SiMO: Single-Modality-Operable Multimodal Collaborative Perception
 
-This repository contains pretrained checkpoints for **SiMO** (Single-Modal-Operable Multimodal Collaborative Perception), a novel framework for robust multimodal collaborative 3D object detection in autonomous driving.
+Official PyTorch implementation of **SiMO**, a framework for robust multimodal collaborative 3D object detection that remains functional even when a key sensor (like LiDAR) fails.
 
-## 📜 Paper
+[[Paper](https://arxiv.org/abs/2603.08240)] [[OpenReview](https://openreview.net/forum?id=h0iRgjTmVs)] [[GitHub](https://github.com/dempsey-wen/SiMO)]
 
-**Title**: Single-Modal-Operable Multimodal Collaborative Perception
-**Conference**: ICLR 2026
-**OpenReview**: [Link](https://openreview.net/forum?id=h0iRgjTmVs)
+**Authors**: Dempsey Wen, Yifan Lu, and others.
 
-## 🚀 Key Features
+## 🚀 Introduction
 
-- **Single-Modal Operability**: Maintains functional performance when one modality fails
-- **LAMMA Fusion**: Length-Adaptive Multi-Modal Fusion module
-- **PAFR Training**: Pretrain-Align-Fuse-Random Drop training strategy
-- **Graceful Degradation**: >80% AP@30 with camera-only operation
+Existing multimodal collaborative perception approaches often fail when a primary modality (like LiDAR) is unavailable due to semantic mismatches. SiMO addresses this through:
+- **LAMMA (Length-Adaptive Multi-Modal Fusion)**: A module that adaptively handles available modalities.
+- **PAFR Training Strategy**: A four-stage paradigm (Pretrain-Align-Fuse-Random Drop) that prevents modality competition and ensures branch independence.
 
 ## 📦 Available Models
 
@@ -58,6 +55,7 @@ This repository contains pretrained checkpoints for **SiMO** (Single-Modal-Opera
 git clone https://github.com/dempsey-wen/SiMO.git
 cd SiMO
 pip install -r requirements.txt
+pip install -e .
 ```
 
 ### Download Checkpoint
@@ -67,27 +65,34 @@ pip install -r requirements.txt
 pip install huggingface-hub
 
 # Download specific checkpoint
-python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='DempseyWen/SiMO', filename='***.pth')"
+python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='DempseyWen/SiMO', filename='SiMO_PF/net_epoch27.pth')"
 ```
 
+### Inference
+
+To run inference on a trained model (e.g., LiDAR+Camera):
+
+```bash
+python opencood/tools/inference.py \
+    --model_dir saved_models/opv2v_lidarcamera_lamma3_pyramid_fusion/ \
+    --fusion_method intermediate
+```
+
+For single-modality testing, modify the config `model.args.single_modality` to `lidar` or `camera` before running the inference script.
 
 ## 📖 Full Documentation
 
-For complete documentation, training scripts, and data preparation instructions, please visit our [GitHub repository](https://github.com/dempsey-wen/SiMO).
+For complete documentation, training scripts, and data preparation instructions, please visit the [GitHub repository](https://github.com/dempsey-wen/SiMO).
 
 ## 🏢 Acknowledgements
 
-This work builds upon:
-- [OpenCOOD](https://github.com/DerrickXuNu/OpenCOOD)
-- [HEAL](https://github.com/yifanlu0227/HEAL)
+This work builds upon [OpenCOOD](https://github.com/DerrickXuNu/OpenCOOD) and [HEAL](https://github.com/yifanlu0227/HEAL).
 
 ## 📄 Citation
 
-If you find this work useful, please cite:
-
 ```bibtex
 @inproceedings{wen2026simo,
-  title={Single-Modal-Operable Multimodal Collaborative Perception},
+  title={Single-Modality-Operable Multimodal Collaborative Perception},
   author={Wen, Dempsey and Lu, Yifan and others},
   booktitle={International Conference on Learning Representations (ICLR)},
   year={2026}
@@ -96,4 +101,4 @@ If you find this work useful, please cite:
 
 ## 📄 License
 
-MIT License - see [LICENSE](https://github.com/dempsey-wen/SiMO/blob/main/LICENSE) for details.
+This project is licensed under the MIT License - see the [LICENSE](https://github.com/dempsey-wen/SiMO/blob/main/LICENSE) file for details.