Use the paper terminology for the fusion variants

README.md

@@ -30,9 +30,9 @@ Non-commercial research use only.
 
 | Path | Backbone | Description |
 |---|---|---|
-| `eccv_gattn/` | SEVA | Main GeoNVS model (gated-attention fusion): `gs_adapter_weights.pth` + `pytorch_lora_weights.safetensors` |
+| `eccv_gattn/` | SEVA | Main GeoNVS model, Adaptive Fusion (`fusion_method: gattn`): `gs_adapter_weights.pth` + `pytorch_lora_weights.safetensors` |
 | `eccv_camctrl/` | CameraCtrl (SVD) | GeoNVS on CameraCtrl: adapter + LoRA |
-| `eccv_base/` | SEVA | Fusion ablation: concat-FeedForward instead of gated attention (use with `configs/module_config/gsadapter_eccv_base.yaml`) |
+| `eccv_base/` | SEVA | Fusion ablation: Naive Fusion (`fusion_method: concat`), use with `configs/module_config/gsadapter_eccv_base.yaml` |
 
 ## Usage