Add pipeline tag and paper link

This PR adds the `image-to-video` pipeline tag to the model card, making it discoverable at the corresponding Hugging Face filter. It also adds a direct link to the paper page (https://huggingface.co/papers/2610.12374) for easier reference.

README.md

@@ -1,21 +1,23 @@
 ---
+base_model: nvidia/Cosmos3-Nano
 license: other
 license_name: openmdw1.1-license
 license_link: https://openmdw.ai/license/1-1/
-base_model: nvidia/Cosmos3-Nano
+pipeline_tag: image-to-video
 tags:
-  - world-model
-  - neural-rendering
-  - video-generation
-  - autoregressive
+- world-model
+- neural-rendering
+- video-generation
+- autoregressive
 ---
 
 # AgentGarten renderer
 
-The real-time neural renderer of [AgentGarten: Code Worlds for Evolving Agents](https://mirros.ai/blog/worlds-for-evolving-agents).
+The real-time neural renderer of [AgentGarten: Code Worlds for Evolving Agents](https://huggingface.co/papers/2610.12374).
 A code world (a simulator or a game engine) keeps the state and runs the rules; this model turns the depth and surface
 normals it exports into the observations an agent sees, block by block.
 
+- Paper: https://huggingface.co/papers/2610.12374
 - Blog: https://mirros.ai/blog/worlds-for-evolving-agents
 - Technical report: https://mirros.ai/report/agent-garten.pdf
 - Project page: https://mirros-lab.github.io/agent-garten
@@ -60,4 +62,4 @@ committed to the key-value cache, so the conditions of the next block can depend
 
 The weights derive from Cosmos3-Nano and are released under the same
 [OpenMDW License Agreement, version 1.1](https://openmdw.ai/license/1-1/). The text tower and the tokenizer are
-NVIDIA's files, redistributed unchanged under that license.
+NVIDIA's files, redistributed unchanged under that license.