docs(README): add Web-DINO row; fix typo + stale KITTI line; tighten prose

Add Web-DINO 7B (2B MC images; DINOv3-report numbers: DAVIS 57.2/65.8/69.5, IN 85.9, ADE20K 42.7, K400 86.8, KITTI 3.2). Fix '~0.5B sample*' typo; drop now-stale 'KITTI still being evaluated' (KITTI filled); tighten summary + demo caption.

README.md

@@ -24,7 +24,7 @@ performance across image and video benchmarks — and leads on DAVIS video track
 <p align="center">
   <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 stays locked on the subject noticeably better than V-JEPA 2.1.</em></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>
 
 - **Architecture**: ViT-7B (embed 4096 / depth 40 / heads 32), patch 16, 3D axial RoPE
   (`base=100`), SwiGLU FFN, LayerScale, per-head QK-norm, gated attention, 4 register tokens.
@@ -106,6 +106,7 @@ single-resolution (S) figure is available.
 |---|---|---|---|---|---|---|---|---|
 | **Motif Vision Encoder** | 0.5B | **74.0** | **80.5** | **83.5** | 87.4 | <u>52.0</u> | 87.4 | 3.2 |
 | DINOv3 | 1.7B | <u>71.1</u> | <u>79.7</u> | <u>83.3</u> | 88.4 | **55.9** | <u>87.8</u> | **2.3** |
+| Web-DINO | 2B | 57.2 | 65.8 | 69.5 | 85.9 | 42.7 | 86.8 | 3.2 |
 | PEcore | 5.4B | 48.2 | 53.1 | 49.8 | **89.3** | 38.9 | **87.9** | 4.1 |
 | SigLIP2 | 10B | 56.1 | 62.3 | 62.9 | <u>89.1</u> | 45.4 | 86.9 | – |
 | OpenCLIP | 2B | – | – | – | – | – | – | – |
@@ -120,10 +121,9 @@ report's unified evaluation (Tab. 3, 5, 6) and ImageNet from Tab. 7; OpenCLIP an
 are not in that report; VideoMAEv2's K400 figure is cited from its own paper (see ‡), and
 OpenCLIP's remaining benchmarks are not reported under a comparable protocol.
 
-Motif sets a new state of the art on DAVIS video segmentation, leading at every resolution
-(74.0 / 80.5 / 83.5 J&F), and stays competitive across the remaining image and video
-benchmarks — despite training on only ~0.5B sample*, roughly 1/3 of DINOv3's data.
-KITTI depth is still being evaluated and will be added as the run completes.
+Motif is state of the art on DAVIS video tracking at every resolution (74.0 / 80.5 / 83.5 J&F)
+and stays competitive on the other image and video benchmarks, using roughly 1/3 of DINOv3's
+training data (~0.5B samples).
 
 
 ## License