Upload README.md

README.md

@@ -1,3 +1,173 @@
+```markdown
 ---
-license: apache-2.0
+license: mit
+pipeline_tag: other
+base_model: Wan-AI/Wan2.2-TI2V-5B
+tags:
+  - pytorch
+  - autonomous-driving
+  - end-to-end-autonomous-driving
+  - world-action-model
+  - trajectory-planning
+  - navsim
 ---
+
+# SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
+
+SimWAM is a World-Action Model for end-to-end autonomous driving. It transfers video-dynamics priors to trajectory prediction by jointly training a pretrained video expert and a lightweight action diffusion transformer with flow matching.
+
+An isolated attention design prevents the action branch from depending on future frames. The video-generation branch is therefore not required during deployment, allowing the trained action expert to operate as a direct trajectory planner.
+
+This repository contains the official released checkpoints for the SimWAM project.
+
+## Task
+
+SimWAM performs end-to-end autonomous-driving trajectory planning on NAVSIM.
+
+The released model uses a single front-facing camera and predicts a future ego trajectory directly from the current observation and conditioning information. The project supports supervised imitation learning and FlowGRPO reinforcement-learning fine-tuning.
+
+Because autonomous-driving trajectory planning does not currently map cleanly to a standard Hugging Face inference pipeline, this repository uses `pipeline_tag: other`.
+
+## Inputs and Outputs
+
+### Inputs
+
+The NAVSIM configuration uses:
+
+- A front-facing RGB camera observation resized to `384 × 672`
+- Precomputed text or scene-context embeddings
+- An 8-dimensional ego-state representation
+- Optional trajectory-planning configuration supplied by the official codebase
+
+### Outputs
+
+The model predicts:
+
+- An eight-step future trajectory
+- Three values per trajectory step in the NAVSIM action representation
+- A tensor with shape `[8, 3]` for one evaluated sample
+
+The released checkpoints use normalized trajectory targets. Dataset statistics and the official NAVSIM evaluation code should be used to convert predictions into the required evaluation representation.
+
+## Checkpoints
+
+| File | Description |
+| --- | --- |
+| `weights/SimWAM.pt` | Supervised SimWAM checkpoint |
+| `weights/SimWAM-RL.pt` | SimWAM checkpoint fine-tuned with FlowGRPO reinforcement learning |
+
+These files are custom PyTorch checkpoints and are not directly loadable with `transformers.AutoModel`.
+
+## Download
+
+Download the complete repository:
+
+```python
+from huggingface_hub import snapshot_download
+
+local_path = snapshot_download(
+    repo_id="H-EmbodVis/SimWAM"
+)
+
+print(local_path)
+```
+
+Download an individual checkpoint:
+
+```python
+from huggingface_hub import hf_hub_download
+
+checkpoint_path = hf_hub_download(
+    repo_id="H-EmbodVis/SimWAM",
+    filename="weights/SimWAM.pt",
+)
+
+print(checkpoint_path)
+```
+
+Command-line download:
+
+```bash
+hf download H-EmbodVis/SimWAM --local-dir ./SimWAM-checkpoints
+```
+
+## Usage
+
+Clone and install the official implementation:
+
+```bash
+git clone https://github.com/H-EmbodVis/SimWAM.git
+cd SimWAM
+
+conda create -n simwam python=3.10 -y
+conda activate simwam
+
+python -m pip install -r requirements.txt
+python -m pip install -e navsim --no-deps
+python -m pip install -e . --no-deps
+```
+
+Place the downloaded checkpoint under `weights/`, then run the official NAVSIM evaluation script:
+
+```bash
+CKPT=./weights/SimWAM.pt \
+TASK=navsim_uncond_front_384x672_1e-4 \
+NPROC_PER_NODE=1 \
+bash experiments/navsim/run_eval_navsim.sh
+```
+
+NAVSIM, nuPlan maps, sensor blobs, text embeddings, normalization statistics, and other required resources must be prepared according to the official project documentation.
+
+## Repository Contents
+
+```text
+.
+├── config.json
+├── README.md
+└── weights
+    ├── SimWAM.pt
+    └── SimWAM-RL.pt
+```
+
+- `README.md` provides the Hugging Face model card and metadata.
+- `config.json` identifies the repository as a custom PyTorch model repository.
+- `weights/SimWAM.pt` contains the supervised checkpoint.
+- `weights/SimWAM-RL.pt` contains the reinforcement-learning checkpoint.
+
+## Performance
+
+The project reports a PDMS score of `91.5` on the NAVSIM `navtest` benchmark using a single front-facing camera.
+
+For complete evaluation settings, comparisons, and reproduction instructions, refer to the official GitHub repository.
+
+## Limitations
+
+- The checkpoints require the official SimWAM implementation.
+- The model is designed for the NAVSIM data format and evaluation pipeline.
+- Performance outside the training and evaluation distributions is not guaranteed.
+- Predictions must not be directly deployed on a physical vehicle without additional validation, safety systems, and human oversight.
+- NAVSIM, nuPlan, OpenScene, Wan2.2, and other upstream resources retain their own licenses and usage terms.
+
+## GitHub
+
+Official implementation:
+
+https://github.com/H-EmbodVis/SimWAM
+
+## License
+
+The SimWAM source repository is released under the MIT License. Third-party code, datasets, pretrained models, and other assets remain subject to their respective licenses.
+
+## Citation
+
+```bibtex
+@article{zhao2026simwam,
+  title   = {A Simple World Action Model for End-to-End Autonomous Driving},
+  author  = {Zhao, Zongchuang and Zhou, Xin and Xu, Tianyang and
+             Sun, Zhengyang and Zhou, Kaixuan and Li, Honglin and
+             Liang, Dingkang and Bai, Xiang},
+  journal = {arXiv preprint},
+  year    = {2026}
+}
+```
+```