assets: refine architecture figure layout and caption legibility

.gitattributes

@@ -35,4 +35,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.gif filter=lfs diff=lfs merge=lfs -text
 assets/architecture.png filter=lfs diff=lfs merge=lfs -text
-assets/dense_attention_comparison.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -22,7 +22,7 @@ Trained on **~1/3 the data of DINOv3** (0.5B vs 1.7B samples), it still reaches
 performance across image and video benchmarks — and leads on DAVIS video tracking.
 
 <p align="center">
-  <img src="assets/haaland_attn_blk20.gif" width="480" alt="Point tracking on a video clip: Motif vs V-JEPA 2.1"/>
+  <img src="assets/haaland_full_attn_blk20.gif" width="480" alt="Point tracking on a video clip: Motif vs V-JEPA 2.1"/>
 </p>
 <p align="center"><em>Point tracking on a video clip (top: Motif, bottom: V-JEPA 2.1) — a query point propagated across frames by patch-feature cosine similarity. Motif tracks the subject more reliably than V-JEPA 2.1.</em></p>
 
@@ -106,7 +106,7 @@ single-resolution (S) figure is available.
 
 | Model | Training<br>data | DAVIS S<br>J&F ↑ | DAVIS M<br>J&F ↑ | DAVIS L<br>J&F ↑ | ImageNet-1K<br>lin. probe ↑ | ADE20K<br>mIoU ↑ | K400 ↑ |
 |---|---|---|---|---|---|---|---|
-| **Motif Vision Encoder** | 0.5B | **73.8** | **80.4** | **83.4** | 87.4 | <u>52.0</u> | 87.4 |
+| **Motif Vision Encoder** | 0.5B | **74.0** | **80.5** | **83.5** | 87.4 | <u>52.0</u> | 87.4 |
 | DINOv3 | 1.7B | <u>71.1</u> | <u>79.7</u> | <u>83.3</u> | 88.4 | **55.9** | <u>87.8</u> |
 | Web-DINO | 2B | 57.2 | 65.8 | 69.5 | 85.9 | 42.7 | 86.8 |
 | PEcore | 5.4B | 48.2 | 53.1 | 49.8 | **89.3** | 38.9 | **87.9** |
@@ -123,15 +123,6 @@ Motif is state of the art on DAVIS video tracking at every resolution (74.0 / 80
 and stays competitive on the other image and video benchmarks, using roughly 1/3 of DINOv3's
 training data (~0.5B samples).
 
-<p align="center">
-  <img src="assets/davis_mask_propagation.gif" width="820" alt="Mask propagation: ground truth vs DINOv3 vs Motif"/>
-</p>
-
-<p align="center">
-  <img src="assets/dense_attention_comparison.png" width="820" alt="Dense attention and feature-similarity comparison across Motif, DINOv3, V-JEPA 2.1, and SigLIP2"/>
-</p>
-<p align="center"><em>Dense features on a single image (768px). Columns: query point, CLS attention, query-point attention, patch-feature cosine similarity. Motif and DINOv3 keep attention and similarity tightly localized on the queried object, while V-JEPA 2.1 and SigLIP2 are noticeably noisier.</em></p>
-
 
 ## License