Update README.md

README.md

@@ -16,7 +16,7 @@ Data, benchmarks, and demos for the Workshop on Human–Scene Interaction Worksh
 
 Given speech, a 3D target coordinate, and a scene, generate SMPL-X pointing gestures that are temporally aligned, spatially accurate, and referentially grounded. Submissions are scored on three axes: temporal alignment, spatial accuracy, and referent recall.
 
-📄 **[Challenge Paper](./hsi_challenge_release_v1.pdf)** · 📦 **[Data & Baseline](./referential-gesture-challenge)** · 🎯 **[Interactive Demo](https://huggingface.co/spaces/mm-conv-scene-gesture/referential-gesture-challenge-demo)**
+📄 **[Challenge Paper](./hsi_challenge_release_v1.pdf)** · 📦 **[Data & Baseline](https://huggingface.co/datasets/hsi-workshop/referential-gesture-challenge)** · 🎯 **[Interactive Demo](https://huggingface.co/spaces/mm-conv-scene-gesture/referential-gesture-challenge-demo)**
 
 ## Resources