Add theme-aware LMM Probe results images to README

Co-authored-by: anxiangsir <31175974+anxiangsir@users.noreply.github.com>

Author: Copilot

README.md

@@ -92,7 +92,13 @@ Performance comparison of different vision encoders using Attentive Probe evalua
 
 Training on a mixed dataset of 740K samples from LLaVA-OneVision and 800K samples from LLaVA-Video SFT. The training pipeline proceeds directly to Stage 2 fine-tuning. We adopt a streamlined native-resolution strategy inspired by LLaVA-OneVision: when the input frame resolution matches the model's native input size, it is fed directly—without tiling or cropping—to evaluate the ViT's native resolution capability.
 
-
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/anxiangsir/asset/main/OneVision/probe_lmm_github_dark.png">
+    <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/anxiangsir/asset/main/OneVision/probe_lmm_github_light.png">
+    <img alt="LMM Probe Results" src="https://raw.githubusercontent.com/anxiangsir/asset/main/OneVision/probe_lmm_github_light.png" width="800" style="max-width: 100%;">
+  </picture>
+</p>
 
 ## 🔧 Setup