Add pipeline tag and link to paper

README.md

@@ -1,12 +1,13 @@
 ---
 license: cc0-1.0
+pipeline_tag: image-to-image
 tags:
-  - world-model
-  - arc-agi-3
-  - test-time-training
-  - next-frame-prediction
-  - vision-transformer
-  - pytorch
+- world-model
+- arc-agi-3
+- test-time-training
+- next-frame-prediction
+- vision-transformer
+- pytorch
 ---
 
 # WARC
@@ -14,6 +15,8 @@ tags:
 [![Code: GitHub](https://img.shields.io/badge/Code-GitHub-black?logo=github)](https://github.com/third-intelligence/WARC)
 [![License: CC0 1.0](https://img.shields.io/badge/License-CC0%201.0-lightgrey)](https://creativecommons.org/publicdomain/zero/1.0/)
 
+**Paper:** [How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time](https://huggingface.co/papers/2611.12324)
+
 WARC (World model for ARC-AGI-3) is a 35M-parameter action-conditioned vision transformer. It
 predicts the next frame of a game, cell by cell, from the last three frames and
 the action, and it keeps learning while an agent plays: after every observed
@@ -110,4 +113,4 @@ The repository lists every third-party component and its licence.
 
 The weights and the code are released under
 [CC0 1.0](https://creativecommons.org/publicdomain/zero/1.0/). Third-party
-components keep their own licences.
+components keep their own licences.