Add pipeline tag, paper, and code links to model card

This PR enhances the model card for `matanru/TalkingPoints` by:
- Adding the `pipeline_tag: image-to-text` to improve discoverability for users looking for models that describe images.
- Linking to the official paper: [Talking Points: Describing and Localizing Pixels](https://huggingface.co/papers/2510.14583).
- Linking to the GitHub repository for easy access to the code and further details: [https://github.com/matanr/Talking_Points](https://github.com/matanr/Talking_Points).

These updates provide essential information and improve the model's visibility on the Hugging Face Hub.

README.md

@@ -1,3 +1,16 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: image-to-text
+---
+
+# Talking Points: Describing and Localizing Pixels
+
+This repository contains the Point Descriptor and Point Localizer models presented in the paper [Talking Points: Describing and Localizing Pixels](https://huggingface.co/papers/2510.14583).
+
+Talking Points introduces a novel framework for pixel-level grounding. It consists of two complementary components: a Point Descriptor that generates rich, contextual descriptions of individual keypoints, and a Point Localizer that regresses precise pixel coordinates from these descriptions. Unlike prior work, our approach produces free-form, coarse-to-fine descriptions that situate keypoints within their visual context.
+
+<div align="center">
+  <img src="https://github.com/matanr/Talking_Points/raw/master/images/teaser.png" alt="Talking Points Teaser Image">
+</div>
+
+For detailed information on installation, dataset creation, training, and evaluation scripts, please refer to the official [GitHub repository](https://github.com/matanr/Talking_Points).