Add pipeline tag and paper link

README.md

@@ -1,14 +1,15 @@
 ---
-license: apache-2.0
+base_model:
+- black-forest-labs/FLUX.2-klein-base-4B
 language:
 - en
+license: apache-2.0
+pipeline_tag: image-to-image
 tags:
 - image-matching
 - dense-correspondence
 - optical-flow
 - image-editing
-base_model:
-- black-forest-labs/FLUX.2-klein-base-4B
 ---
 
 # FreeMatching
@@ -17,7 +18,7 @@ base_model:
 
 Luping Liu, Bingyi Kang, Yifan Wang, Dong Xu
 
-[Project repository](https://github.com/luping-liu/FreeMatching)
+[Paper](https://huggingface.co/papers/2610.12421) · [Project repository](https://github.com/luping-liu/FreeMatching)
 
 FreeMatching combines generative and semantic foundation representations, heterogeneous correspondence supervision, and teacher-guided iterative refinement for dense correspondence, including image editing and reference-guided generation.
 
@@ -60,4 +61,4 @@ Due to the size of the video data and copyright restrictions on the source video
 
 ## Validation
 
-Both snapshots were exported as tensor-only safetensors. Every tensor name and shape was checked against the release architecture, and uploaded file sizes and SHA-256 hashes were verified. CPU checks cover the custom transformer, correspondence warping, checkpoint loading, and trajectory conversion; this packaging pass does not include a full GPU inference or retraining validation.
+Both snapshots were exported as tensor-only safetensors. Every tensor name and shape was checked against the release architecture, and uploaded file sizes and SHA-256 hashes were verified. CPU checks cover the custom transformer, correspondence warping, checkpoint loading, and trajectory conversion; this packaging pass does not include a full GPU inference or retraining validation.