Add pipeline tag and library name

This PR adds the `pipeline_tag: image-to-3d` to the metadata, ensuring the model can be found on the Hub. I also added `library_name: pytorch`.

README.md

@@ -1,9 +1,11 @@
 ---
+language:
+- en
 license: other
 license_name: nvidia-non-commercial-license
 license_link: https://huggingface.co/nvidia/PartPacker/blob/main/LICENSE
-language:
-- en
+pipeline_tag: image-to-3d
+library_name: pytorch
 ---
 
 # Model Card for PartPacker
@@ -30,7 +32,7 @@ It's intended to be used by researchers and academics to develop new 3D generati
 
 ## Reference(s)
 [Code](https://github.com/NVlabs/PartPacker)  
-[Paper](https://arxiv.org/abs/TODO)  
+[Paper](https://arxiv.org/abs/2506.09980)  
 
 ## Model Architecture
 **Architecture Type:** Transformer    
@@ -88,4 +90,4 @@ For the Flow model, we use all 254K meshes for training.
 ## Ethical Considerations
 NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
 
-Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
+Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).