Update pipeline tag to image-to-video and add paper link

README.md

@@ -1,14 +1,14 @@
 ---
-license: apache-2.0
 base_model: Wan-AI/Wan2.2-TI2V-5B
-pipeline_tag: text-to-video
+license: apache-2.0
+pipeline_tag: image-to-video
 ---
 
 # PhyRAG Wan2.2 TI2V-5B
 
 > Authors: Kexu Cheng, Zicheng Liu, Mingju Gao, Chunhe Song, Hao Tang  
 > Project page: https://sediment1024.github.io/PhysRAG/ 
-> Paper: *PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation* (coming soon)  
+> Paper: [PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation](https://huggingface.co/papers/2606.26916)  
 > Code: https://github.com/sediment1024/PhysRAG  
 > Dataset: https://huggingface.co/datasets/sediment1024/PhysRAG  
 
@@ -41,8 +41,6 @@ The SHA-256 checksum is
 2. PhyRAG 170-video RAG library and FAISS index
 3. VideoCLIP-XL retriever checkpoint
 
-The paper link will be added once the public manuscript page is available.
-
 ## Citation
 
 ```bibtex
@@ -55,4 +53,4 @@ The paper link will be added once the public manuscript page is available.
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2606.26916}, 
 }
-```
+```