Add pipeline tag, links to paper, project page and code

Hi, I'm Niels from the community team at Hugging Face.

This PR improves the model card for the MNIST World models by:
- Adding the `image-to-video` pipeline tag to the metadata.
- Including links to the [research paper](https://huggingface.co/papers/2601.01075), [project website](https://flowequivariantworldmodels.github.io/), and the [official GitHub repository](https://github.com/hlillemark/flowm).
- Adding a BibTeX citation for the work.

Feel free to merge if this looks good!

README.md

@@ -1,11 +1,35 @@
+---
+pipeline_tag: image-to-video
+---
+
 # MNIST World Models
 
-This repository hosts a curated set of checkpoints used for experiments of FloWM: https://huggingface.co/papers/2601.01075.
+This repository hosts a curated set of checkpoints used for experiments in the paper [Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments](https://huggingface.co/papers/2601.01075).
+
+[**Project Page**](https://flowequivariantworldmodels.github.io/) | [**GitHub**](https://github.com/hlillemark/flowm)
+
+## Description
+Flow Equivariant World Modeling (FloWM) is a framework that leverages time-parameterized symmetries within a latent memory for stable and accurate dynamics prediction over long horizons. The latent memory shifts and transforms equivariantly with self-motion and inferred external object motion, keeping information about out-of-view regions aligned as time progresses. These specific checkpoints correspond to the **MNIST World** (2D) environment benchmarks.
 
 ## Contents
-- `mnistworld/dfot/dynamic_po.ckpt` — mnistworld dfot dynamic_po
-- `mnistworld/dfot-ssm/dynamic_po.ckpt` — mnistworld dfot-ssm dynamic_po
-- `mnistworld/flowm-fernn/dynamic_po_flowm.pt` — mnistworld flowm (fernn) dynamic_po_flowm
-- `mnistworld/vae/mnist_world_vae.ckpt` — mnistworld vae
+This repository contains the following checkpoints:
+- `mnistworld/dfot/dynamic_po.ckpt` — MNIST World Diffusion Forcing Transformer (DFoT)
+- `mnistworld/dfot-ssm/dynamic_po.ckpt` — MNIST World Diffusion State Space Model (DFoT-SSM)
+- `mnistworld/flowm-fernn/dynamic_po_flowm.pt` — MNIST World FloWM (FERN-N)
+- `mnistworld/vae/mnist_world_vae.ckpt` — MNIST World VAE
+
+## Usage
+For detailed instructions on environment setup, training, and inference (including replicating the paper's results), please refer to the [official GitHub repository](https://github.com/hlillemark/flowm) and its [wiki](https://github.com/hlillemark/flowm/wiki).
 
-Hub: https://huggingface.co/flowm123/mnistworld-models
+## Citation
+```bibtex
+@misc{lillemark2026flowequivariantworldmodels,
+    title={Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments}, 
+    author={Hansen Jin Lillemark and Benhao Huang and Fangneng Zhan and Yilun Du and Thomas Anderson Keller},
+    year={2026},
+    eprint={2601.01075},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG},
+    url={https://arxiv.org/abs/2601.01075}, 
+  }
+```