update README.md

README.md

@@ -1,7 +1,6 @@
 ---
-license: apache-2.0
+license: mit
 library_name: transformers
-base_model: []
 tags:
   - gaze-estimation
   - gaze-target-estimation
@@ -9,11 +8,12 @@ tags:
 pipeline_tag: image-feature-extraction
 ---
 
-# PaGE-ViT-H+
+# PaGE ViT-H+
 
-Huge+ flagship variant. Fine-tuned. Part of the [PaGE](https://huggingface.co/Octopus1/PaGE) gaze target estimation family.
+Huge+ flagship teacher; finetuned end-to-end. Part of the [PaGE](https://huggingface.co/Octopus1/PaGE) gaze target estimation family
+(ICLR 2026).
 
-- **Backbone:** DINOv3 ViT-H+/16 (gated MLP)
+- **Backbone:** DINOv3 ViT-H+ (gated MLP) (derivative of DINOv3, full-parameter trained)
 - **Params:** ~1.7B
 - **Scene input:** 512×512, **Head input:** 256×256, **Heatmap output:** 64×64
 - **Source checkpoint:** `vithplus_ft.pt`
@@ -21,8 +21,11 @@ Huge+ flagship variant. Fine-tuned. Part of the [PaGE](https://huggingface.co/Oc
 ## Self-contained weights
 
 This checkpoint includes the full DINOv3 backbone weights in its `safetensors` files. **No external
-DINOv3 weights are downloaded.** The model code (`modeling_page.py`) is loaded automatically from
-[`Octopus1/PaGE`](https://huggingface.co/Octopus1/PaGE) via `auto_map` when you pass `trust_remote_code=True`.
+DINOv3 weights are downloaded** — the DINOv3 model *structure* is provided by `transformers>=4.56`
+(built-in `dinov3_vit`), and the backbone weights here are derivative weights from full-parameter
+training of DINOv3. The model code (`modeling_page.py`) is loaded automatically from
+[`Octopus1/PaGE`](https://huggingface.co/Octopus1/PaGE) via `auto_map` when you pass
+`trust_remote_code=True`.
 
 ## Installation
 
@@ -55,7 +58,7 @@ inout   = out["inout"][0]     # [Np]
 
 ## Inputs / Outputs
 
-See the family [README](https://huggingface.co/Octopus1/PaGE) for the full input/output spec.
+See the family [README](https://huggingface.co/Octopus1/PaGE) for the full spec.
 
 - Input dict: `images` (list of `[B,3,512,512]`), `head_images` (list of `[sum(Np),3,256,256]`),
   `bboxes` (per-image list of `(xmin,ymin,xmax,ymax)` in `[0,1]`).
@@ -63,4 +66,15 @@ See the family [README](https://huggingface.co/Octopus1/PaGE) for the full input
 
 ## License
 
-Apache-2.0.
+- The PaGE decoder and gaze heads are released under the **MIT License** (see `LICENSE`).
+- The **DINOv3 backbone is a derivative work of DINOv3** ([facebook/dinov3](https://huggingface.co/facebook/dinov3)).
+  The backbone was initialized from the public DINOv3 self-supervised weights and then **trained in
+  full (all parameters updated)** as part of PaGE training — i.e. the backbone weights here are
+  **derivative weights produced by full-parameter training of DINOv3**, not the original DINOv3
+  weights verbatim.
+- DINOv3 is released by Meta AI under the **Meta DINO License** (see `DINOv3_LICENSE.md`). Under its
+  Section 1.b.i, derivative works of DINOv3 (including these backbone weights) are distributed under
+  the DINO License terms, and `DINOv3_LICENSE.md` must accompany any redistribution.
+- By using or redistributing this model you agree to the DINO License for the DINOv3-derived portions.
+
+See the family [README](https://huggingface.co/Octopus1/PaGE) for full license details.