Add pipeline tag and GitHub link

README.md

@@ -1,10 +1,12 @@
 ---
 library_name: transformers
+pipeline_tag: zero-shot-image-classification
 tags:
 - vision
 - uncertainty
 - hyperbolic
 ---
+
 # UNCHA: Uncertainty-guided Compositional Hyperbolic Alignment
 
 ## Overview
@@ -19,9 +21,9 @@ Unlike conventional vision-language models, UNCHA explicitly captures the fact t
 
 To address this, UNCHA introduces **uncertainty-aware alignment in hyperbolic space**, enabling better hierarchical and compositional reasoning.
 
-Project Page: https://jeeit17.github.io/UNCHA-project_page/
-
-Paper: https://arxiv.org/abs/2603.22042
+- **Project Page:** [https://jeeit17.github.io/UNCHA-project_page/](https://jeeit17.github.io/UNCHA-project_page/)
+- **Paper:** [Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models](https://arxiv.org/abs/2603.22042)
+- **Code:** [https://github.com/jeeit17/UNCHA](https://github.com/jeeit17/UNCHA)
 
 --- 
 ## Download 
@@ -129,7 +131,7 @@ python scripts/evaluate.py \
 ```bibtex
 @inproceedings{kim2026uncha,
   author    = {Kim, Hayeon and Jang, Ji Ha and Kim, Junghun James and Chun, Se Young},
-  title     = {UNCHA: Uncertainty-guided Compositional Hyperbolic Alignment with Part-to-Whole Semantic Representativeness},
+  title     = {UNCHA: Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models},
   booktitle = {CVPR},
   year      = {2026},
 }
@@ -139,6 +141,4 @@ python scripts/evaluate.py \
 ## Acknowledgements
 
 This work is supported by IITP, NRF, MSIT, and Seoul National University programs.
-We also acknowledge prior works including MERU, HyCoCLIP, and ATMG.
-
----
+We also acknowledge prior works including MERU, HyCoCLIP, and ATMG.