Model card: checkpoint table

README.md

@@ -36,6 +36,7 @@ One folder per finished run: `model.safetensors` (EMA weights), `config.json` (m
 | `S_arms_nocam/` | EG-SWM, no camera action | S | 60000 | 21.52 | 0.176 | 215 | – |
 | `S_arms/` | EG-SWM | S | 60000 | 22.00 | 0.164 | 186 | 0.70 |
 | `S_arms_scene/` | EG-SWM + scene action | S | 60000 | 22.38 | 0.156 | 174 | 0.22 |
+| `S_arms_nofwd/` | EG-SWM, diffusion loss only | S | 60000 | 21.65 | 0.172 | 204 | 0.69 |
 | `S_arms_poolglobal/` | EG-SWM, arm actions not grounded | S | 60000 | 22.07 | 0.163 | 188 | 0.65 |
 
 Loading (with the `swm` package from the [code repository](https://github.com/GIND123/Surgical-World-Model)):
@@ -50,6 +51,8 @@ model = WorldModel(WMConfig.from_dict(meta["model"])).eval()
 load_model(model, "S_arms/model.safetensors")
 ```
 
+The SurgWM re-implementation (`surgwm/`) has one file per stage (`tokenizer`, `lam`, `dynamics`), loaded into the classes of `swm.baselines.surgwm` with `SurgWMConfig(**meta["model"])`.
+
 ## Training data
 
 * **SurgVU** (Zia et al., *Surgical Visual Understanding (SurgVU) Dataset*, arXiv:2501.09209): 155 da Vinci porcine training-lab cases, 837.8 h, with robot-log instrument and endoscope occupancy per arm.