Add paper link to model card

README.md

@@ -1,12 +1,17 @@
 ---
-license: cc-by-nc-4.0
-language:
-- en
-library_name: pytorch
 base_model:
 - facebook/ijepa_vith16_1k
 datasets:
 - dralois/Bar-JEPA
+language:
+- en
+library_name: pytorch
+license: cc-by-nc-4.0
+metrics:
+- f1
+- accuracy
+- precision
+- recall
 pipeline_tag: keypoint-detection
 tags:
 - bar-chart
@@ -17,11 +22,6 @@ tags:
 - synthetic
 - keypoint-detection
 - self-supervised
-metrics:
-- f1
-- accuracy
-- precision
-- recall
 model-index:
 - name: Bar-JEPA (kp-cl-arp-ctt-ft)
   results:
@@ -33,17 +33,17 @@ model-index:
       type: real-world
     metrics:
     - type: f1
-      name: Bar Keypoint F1
       value: 0.785
+      name: Bar Keypoint F1
     - type: f1
-      name: Tick Keypoint F1
       value: 0.842
+      name: Tick Keypoint F1
     - type: accuracy
-      name: Value Accuracy (ε=0.05)
       value: 0.499
+      name: Value Accuracy (ε=0.05)
     - type: accuracy
-      name: Value Accuracy (ε=0.02)
       value: 0.365
+      name: Value Accuracy (ε=0.02)
   - task:
       type: keypoint-detection
       name: Bar Chart Value Extraction
@@ -52,24 +52,24 @@ model-index:
       type: dralois/Bar-JEPA
     metrics:
     - type: f1
-      name: Bar Keypoint F1
       value: 0.961
+      name: Bar Keypoint F1
     - type: f1
-      name: Tick Keypoint F1
       value: 0.951
+      name: Tick Keypoint F1
     - type: accuracy
-      name: Value Accuracy (ε=0.05)
       value: 0.792
+      name: Value Accuracy (ε=0.05)
     - type: accuracy
-      name: Value Accuracy (ε=0.02)
       value: 0.657
+      name: Value Accuracy (ε=0.02)
 ---
 
 # Bar-JEPA
 
 Per-bar numerical value recovery from vertical bar chart images. A self-supervised I-JEPA encoder (ViT-H, finetuned on synthetic bar charts) produces feature maps consumed by a lightweight keypoint decoder. The decoder outputs heatmaps for bar corners, value-axis ticks and the coordinate origin, which are post-processed with NMS, OCR and RANSAC regression to recover numerical bar values.
 
-**Paper:** *Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture* — Poonam, Epple & Ropinski, Ulm University (ICDAR 2026).  
+**Paper:** [*Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture*](https://huggingface.co/papers/2608.06062) — Poonam, Epple & Ropinski, Ulm University (ICDAR 2026).  
 **Code:** [github.com/dralois/Bar-JEPA](https://github.com/dralois/Bar-JEPA)
 
 ## Pipeline