Upload README.md with huggingface_hub

README.md

@@ -22,7 +22,7 @@ conda env create -f environment.yml
 conda activate gld
 
 # Download all checkpoints
-huggingface-cli download SeonghuJeon/GLD --local-dir .
+python -c "from huggingface_hub import snapshot_download; snapshot_download('SeonghuJeon/GLD', local_dir='.')"
 
 # Run demo
 ./run_demo.sh da3
@@ -41,16 +41,5 @@ huggingface-cli download SeonghuJeon/GLD --local-dir .
 | `pretrained_models/mae_decoder.pt` | DA3 MAE decoder (EMA, decoder-only) | 423M | 1.6G |
 | `pretrained_models/vggt/mae_decoder.pt` | VGGT MAE decoder (EMA, decoder-only) | 425M | 1.6G |
 
-Stage-2 and MAE decoder checkpoints contain **EMA weights only**.  
+Stage-2 and MAE decoder checkpoints contain **EMA weights only**.
 MAE decoder checkpoints contain **decoder weights only** (encoder removed).
-
-## Citation
-
-```bibtex
-@article{jang2026gld,
-  title={Repurposing Geometric Foundation Models for Multi-view Diffusion},
-  author={Jang, Wooseok and Jeon, Seonghu and Han, Jisang and Choi, Jinhyeok and Kwon, Minkyung and Kim, Seungryong and Xie, Saining and Liu, Sainan},
-  journal={arXiv preprint},
-  year={2026}
-}
-```