GlobalDiff official checkpoints

Official checkpoints for Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints (AAAI 2026), a diffusion approach to long-horizon co-speech gesture generation.

• Paper · Hugging Face Paper page
• Project page · Code
• Published version
• Generated inference data

Files

The checkpoint files mirror the official repository while preserving their repository-relative paths:

Path	Role
Scripts/VAE/ckpt/split/global/MaskedVAE2-HorizonFlip/best.pt	Global rotation VAE checkpoint
Scripts/VAE/ckpt/split/global/MaskedVAE3-HorizonFlip/best.pt	Global rotation VAE checkpoint
Scripts/FM/ckpt/split/SimpleSpeechModel/best.zip	Speech model checkpoint archive
Scripts/FM/EMAGE_VAE/AESKConv_240_100.bin	Evaluation/representation asset
See the code repository's environment checker and inference instructions for all runtime dependencies.

Verify the files from the repository root with sha256sum -c SHA256SUMS.

Terms

This repository mirrors research artifacts released by the authors. No new license is granted by this model card. Code, BEAT2, SMPL-X, pretrained encoders, and other third-party assets remain subject to their respective terms.

Citation

@inproceedings{zhang2026globaldiff,
  title={Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints},
  author={Zhang, Xiangyue and Li, Jianfang and Ren, Jianqiang and Zhang, Jiaxu},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={40},
  number={15},
  pages={12834--12842},
  year={2026},
  doi={10.1609/aaai.v40i15.38281}
}