Add pipeline tag, license, and paper link

README.md

@@ -1,22 +1,24 @@
 ---
+datasets:
+- HamiFormer/Hamiballs
 language:
-  - en
+- en
 library_name: pytorch
+license: mit
+pipeline_tag: time-series-forecasting
 tags:
-  - physics
-  - physical-simulation
-  - trajectory-prediction
-  - hamiltonian
-  - diffusion
-datasets:
-  - HamiFormer/Hamiballs
+- physics
+- physical-simulation
+- trajectory-prediction
+- hamiltonian
+- diffusion
 ---
 
 # HamiFormer models
 
-Inference weights for HamiFormer and baseline models on HamiBalls-1 and HamiBalls-2. HamiFormer combines whole-window diffusion prediction with Hamiltonian propagation through affine symplectic maps and regime-conditioned corrections.
+Inference weights for HamiFormer and baseline models on HamiBalls-1 and HamiBalls-2. HamiFormer combines whole-window diffusion prediction with Hamiltonian propagation through affine symplectic maps and regime-conditioned corrections. This model is described in the paper [HamiFormer: Dual-Expert Diffusion Fields with Affine Symplectic Maps](https://huggingface.co/papers/2609.32838).
 
-[Code and instructions](https://github.com/HamiFormer/HamiFormer) · [HamiBalls datasets](https://huggingface.co/datasets/HamiFormer/Hamiballs)
+[Code and instructions](https://github.com/starx237/HamiFormer) · [HamiBalls datasets](https://huggingface.co/datasets/HamiFormer/Hamiballs) · [Project page](https://hamiformer.github.io/)
 
 ## Available weights
 
@@ -38,7 +40,7 @@ Files contain tensor dictionaries loaded by the corresponding implementations in
 Use Python 3.10–3.12, PyTorch 2.5.1, and a compatible CUDA environment.
 
 ```sh
-git clone https://github.com/HamiFormer/HamiFormer.git
+git clone https://github.com/starx237/HamiFormer.git
 cd HamiFormer
 python -m pip install -e ".[test,data,analysis]"
 python -m pip install huggingface_hub
@@ -88,4 +90,4 @@ components = model.components()
 
 These models support research on learned physical simulation and trajectory prediction in the HamiBalls spring-and-contact environments. The matching dataset conventions, physical time step, and object representation are described in the [dataset card](https://huggingface.co/datasets/HamiFormer/Hamiballs).
 
-The project code is distributed under the [MIT license](https://github.com/HamiFormer/HamiFormer/blob/main/LICENSE). See [third-party notices](https://github.com/HamiFormer/HamiFormer/blob/main/THIRD_PARTY_NOTICES.md) for baseline references and attribution.
+The project code is distributed under the [MIT license](https://github.com/starx237/HamiFormer/blob/main/LICENSE). See [third-party notices](https://github.com/starx237/HamiFormer/blob/main/THIRD_PARTY_NOTICES.md) for baseline references and attribution.