Improve model card with paper links and usage

README.md

@@ -1,27 +1,28 @@
 ---
-license: apache-2.0
+base_model: Wan-AI/Wan2.1-T2V-1.3B
 language:
 - en
+license: apache-2.0
+pipeline_tag: text-to-video
 tags:
 - text-to-video
 - video-generation
 - human-motion
 - reinforcement-learning
 - lora
-base_model: Wan-AI/Wan2.1-T2V-1.3B
-pipeline_tag: text-to-video
 ---
 
 # PhyMotion — Causal Forcing 1.3B
 
-LoRA adapter for **Causal Forcing 1.3B** (the autoregressive distilled version of Wan2.1 T2V-1.3B),
-post-trained with RL using the **PhyMotion** reward — a structured 3D motion reward grounded in
-SMPL recovery + MuJoCo inverse dynamics.
+LoRA adapter for **Causal Forcing 1.3B** (the autoregressive distilled version of Wan2.1 T2V-1.3B), post-trained with RL using the **PhyMotion** reward — a structured 3D motion reward grounded in SMPL recovery and MuJoCo inverse dynamics.
+
+* **Paper:** [PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation](https://huggingface.co/papers/2605.14269)
+* **Project Page:** https://phy-motion.github.io
+* **Repository:** https://github.com/h6kplus/PhyMotion
+* **Prompt Dataset:** [6kplus/PhyMotion-MotionX-Prompts](https://huggingface.co/datasets/6kplus/PhyMotion-MotionX-Prompts)
 
-* Project page: https://phy-motion.github.io
-* Training code: https://github.com/h6kplus/PhyMotion
-* Prompt dataset: https://huggingface.co/datasets/6kplus/PhyMotion-MotionX-Prompts
-* Paper: *PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation*
+## Description
+Generating realistic human motion is a central yet unsolved challenge in video generation. PhyMotion is a structured, fine-grained motion reward that grounds recovered 3D human trajectories in a physics simulator and evaluates motion quality along multiple dimensions of physical feasibility: kinematic plausibility, contact and balance consistency, and dynamic feasibility.
 
 ## What's in this repo
 
@@ -30,13 +31,9 @@ SMPL recovery + MuJoCo inverse dynamics.
 | `adapter_model.bin` | PEFT LoRA weights (rank 256, targets `CausalWanAttentionBlock`) |
 | `adapter_config.json` | LoRA configuration |
 
-The training/eval prompt lists live in a separate dataset repo:
-[`6kplus/PhyMotion-MotionX-Prompts`](https://huggingface.co/datasets/6kplus/PhyMotion-MotionX-Prompts).
-
 ## Usage
 
-Clone the PhyMotion training repo, place the base model checkpoint and this LoRA, then run
-inference (full command in the project README):
+To use this LoRA adapter, clone the [PhyMotion repository](https://github.com/h6kplus/PhyMotion), place the base model checkpoint and this LoRA, then run inference (full instructions available in the repository README):
 
 ```bash
 git clone https://github.com/h6kplus/PhyMotion.git
@@ -51,6 +48,7 @@ huggingface-cli download 6kplus/PhyMotion-MotionX-Prompts \
   --repo-type dataset --local-dir dataset/motionx
 
 # Inference
+# Note: You still need the base Causal Forcing 1.3B checkpoint (causal_forcing.pt)
 torchrun --nproc_per_node=1 scripts/inference_wan.py \
   --base_model checkpoints/causalforcing/chunkwise/causal_forcing.pt \
   --lora_path  checkpoints/phymotion-causalforcing \
@@ -63,9 +61,6 @@ torchrun --nproc_per_node=1 scripts/inference_wan.py \
   --mixed_precision bf16 --seed 42
 ```
 
-You still need the **base Causal Forcing 1.3B checkpoint** (`causal_forcing.pt`). See the project
-page for the download link.
-
 ## Citation
 
 ```bibtex
@@ -74,11 +69,11 @@ page for the download link.
   author  = {Huang, Yidong and Wang, Zun and Lin, Han and Kim, Dong-Ki and
              Omidshafiei, Shayegan and Yoon, Jaehong and Cho, Jaemin and
              Zhang, Yue and Bansal, Mohit},
-  journal = {arXiv preprint},
+  journal = {arXiv preprint arXiv:2605.14269},
   year    = {2026}
 }
 ```
 
 ## License
 
-Apache 2.0. The base Wan2.1 / Causal Forcing weights retain their original license.
+Apache 2.0. The base Wan2.1 / Causal Forcing weights retain their original license.