Update README.md

README.md

@@ -16,8 +16,12 @@ Training checkpoints for [ForgeWM](https://github.com/asdfo123/ForgeWM).
 | File | Stage | Description |
 |------|-------|-------------|
 | `stage0/model.pt` | Stage 0 | Bidirectional SFT (domain adaptation, 4000 steps) |
+| `stage1/model.pt` | Stage 1 | Teacher-Forcing Causal AR (10000 steps) |
+| `stage2/model.pt` | Stage 2 | Consistency Distillation (6000 steps) |
 | `stage3/model.pt` | Stage 3 | DMD final model (4-step real-time inference) |
 
+
+
 ## Usage
 
 ```bash
@@ -29,5 +33,18 @@ python inference.py --checkpoint_path ckpts/stage3/model.pt --image_path demo_im
 ```
 
 ## 🚧 Coming Soon
-- Stage 1 (Teacher-Forcing AR) checkpoint
-- Stage 2 (Consistency Distillation) checkpoint
+- More intermediate checkpoints
+
+## Citation
+
+```bibtex
+@misc{forgewm2026,
+  title={ForgeWM: A Reproducible Training Recipe for Action-Controllable World Models},
+  author=ForgeWM Team,
+  year={2026},
+  url={https://github.com/asdfo123/ForgeWM}
+}
+```
+
+## Contact
+[Xinye Li](https://asdfo123.github.io) leeasdfo123@gmail.com