Restore original EKT-Router paper title

README.md

@@ -3,20 +3,20 @@ language:
 - en
 pipeline_tag: image-text-to-text
 tags:
-- knowinrouter
+- ekt-router
 - embodied-question-answering
 - lora
 - coming-soon
 ---
-# KnowinRouter — model release placeholder
+# EKT-Router: Expert–Evidence Alignment for Embodied Vision–Language Models
 
-**Coming soon. No model weights or adapters are available to download.**
+**Model release placeholder. Coming soon. No model weights or adapters are available to download.**
 This repository contains a model card only. It is not a loadable Transformers model.
 No release date is promised, and no third-party weights have been uploaded.
 
 ## Model description
 
-KnowinRouter jointly selects one capability expert and optional knowledge/perception
+EKT-Router jointly selects one capability expert and optional knowledge/perception
 under a bounded acquisition budget. The intended portfolio uses a shared
 Qwen3-VL-8B backbone and three independent LoRA adapters: General (continued
 pretraining), Spatial Reasoning, and Spatiotemporal. A frozen Qwen3-VL-2B descriptor