Add paper and code links

README.md

@@ -1,18 +1,21 @@
 ---
+base_model: MiniMaxAI/MiniMax-H3
+library_name: pytorch
 license: other
 license_name: minimax-h3-community
 license_link: LICENSE
-library_name: pytorch
 pipeline_tag: image-to-video
-base_model: MiniMaxAI/MiniMax-H3
 tags:
-  - lora
-  - audio-video-generation
-  - reference-to-video
-  - streaming
-  - safetensors
+- lora
+- audio-video-generation
+- reference-to-video
+- streaming
+- safetensors
 ---
 
+**Paper:** [TaoMate-R1: Temporal Role Specialization for Streaming Multi-Reference Video Generation](https://huggingface.co/papers/2611.14307)  
+**Code:** [TaoMate-H3](https://github.com/TaoLiveAIGC/TaoMate-H3)
+
 # TaoMate-R1
 
 Reference-conditioned streaming audio-video generation built on
@@ -74,4 +77,4 @@ audio is generated by the model. The result is `outputs/ref2av/video.mp4`.
 
 This release follows the [MiniMax H3 Community License Agreement](LICENSE).
 We thank MiniMax, Qwen, PyTorch, and the Self Forcing authors for their models,
-implementations, and research.
+implementations, and research.