docs(README): condense results prose to DAVIS-SOTA + competitive summary

Replace the detailed per-benchmark bullet list with a concise summary: SOTA on DAVIS, competitive elsewhere on ~1/3 of DINOv3's data; keep KITTI-pending note.

README.md

@@ -115,20 +115,10 @@ single-resolution (S) figure is available.
 
 <sub>‡ VideoMAEv2 ViT-g: K400 top-1 after **full fine-tuning**, not the frozen attentive-probe protocol used for the other rows.</sub>
 
-- **DAVIS video segmentation (J&F)** — leads at every resolution: **74.0 (S) / 80.5 (M) /
-  83.5 (L)**, surpassing DINOv3 7B (71.1 / 79.7 / 83.3) across the board, reflecting the
-  encoder's dense, temporally-coherent patch features on video.
-- **ADE20K semantic segmentation (52.0 mIoU)** is second only to DINOv3 7B (55.9), well ahead
-  of PEcore, SigLIP2, and V-JEPA 2.1.
-- **ImageNet-1K linear probe (87.2)** is close to DINOv3 (88.4) and behind the contrastively
-  trained SigLIP2 (89.1) and PEcore (89.3) — notable given Motif sees **0.5B** samples versus
-  PEcore's **5.4B** and SigLIP2's **10B** image–text pairs.
-- **Data efficiency** — these results come from **~0.47B training samples** (448.6M images +
-  18.5M video clips), roughly **3.6× less data than DINOv3**, which is trained on LVD-1689M
-  (1,689M images). Despite the smaller corpus — and with only ~4% of samples being video — the
-  encoder stays competitive across both image and video benchmarks, and leads on DAVIS.
-- KITTI depth estimation is still being evaluated and will be added as the run completes.
-  Numbers in this table will be updated as evaluations finish.
+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 samples**, roughly **1/3 of DINOv3's data**.
+KITTI depth is still being evaluated and will be added as the run completes.
 
 Protocol: DINOv3-style linear/attentive probes for image tasks; V-JEPA 2-style protocol for
 video. Baseline DAVIS / ADE20K / K400 / KITTI figures are taken from the DINOv3 technical