luisf-mc
/

gui-g2-3b-ccf

@@ -23,7 +23,7 @@ metrics:
 A drop-in inference wrapper that improves GUI-G2-3B's icon-grounding accuracy by **+2.2pp on ScreenSpot-v2** at zero training cost. The base weights are unchanged; everything is in the inference pipeline.
 > **Try it live (Azure A100, scale-to-zero)**: <https://guigrounding.whiteplant-27564a0e.eastus.azurecontainerapps.io>
-> Warm latency: **~2s/request (fast mode)** with CCF refinement, or ~8s for accurate mode (7-pass self-consistency, real agreement-based confidence). Cold start ~90s the first time after idle.
 ![Side-by-side: 4 ScreenSpot-v2 icons where GUI-G2-3B baseline misses (red X) and CCF hits (green check). Blue boxes are ground truth.](comparison.png)

 A drop-in inference wrapper that improves GUI-G2-3B's icon-grounding accuracy by **+2.2pp on ScreenSpot-v2** at zero training cost. The base weights are unchanged; everything is in the inference pipeline.
 > **Try it live (Azure A100, scale-to-zero)**: <https://guigrounding.whiteplant-27564a0e.eastus.azurecontainerapps.io>
+> Warm latency: **~250-400ms server time / ~700-900ms wall time** for fast mode (CCF), **~900ms server time / ~1.6s wall** for accurate mode (6-pass self-consistency with real agreement-based confidence). The playground also streams the coarse CCF prediction at ~600ms wall so the dot appears tentatively before the refined pass completes. Cold start ~90s the first time after idle.
 ![Side-by-side: 4 ScreenSpot-v2 icons where GUI-G2-3B baseline misses (red X) and CCF hits (green check). Blue boxes are ground truth.](comparison.png)