Downloads · 30 days
0
vr-hmr
zirobtc/vr-hmr
vr-hmr is a machine learning model from zirobtc. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
<p align="center" <h1 align="center" GEM: A Generalist Model for Human Motion</h1 <p align="center" <a href="https://jeffli.site/"<strongJiefeng Li</strong</a · <a href="https://www.jinkuncao.com/"<strongJinkun Cao</s…
Access
Public
Updated Mar 3, 2026
Repo size
42.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth14.6 GB · 35%
At a glance
- Access
- Public
- Created
- Feb 28, 2026
- Updated
- Mar 3, 2026
- SHA
- 71789375
Model card
From the Hugging Face model README
<p align="center">
<h1 align="center"> GEM: A Generalist Model for Human Motion</h1>
<p align="center">
<a href="https://jeffli.site/"><strong>Jiefeng Li</strong></a>
·
<a href="https://www.jinkuncao.com/"><strong>Jinkun Cao</strong></a>
·
<a href="https://cs.stanford.edu/~haotianz/"><strong>Haotian Zhang</strong></a>
·
<a href="https://davrempe.github.io/"><strong>Davis Rempe</strong></a>
·
<a href="https://jankautz.com/"><strong>Jan Kautz</strong></a>
·
<a href="https://www.umariqbal.info/"><strong>Umar Iqbal</strong></a>
·
<a href="https://ye-yuan.com/"><strong>Ye Yuan</strong></a>
</p>
<h2 align="center">ICCV 2025 (Highlight)</h2>
<div align="center">
<img src="./assets/teaser.png" alt="Logo" width="100%">
</div>
</p>
<p align="center">
<a href="https://research.nvidia.com/labs/dair/gem/"><img src="https://img.shields.io/badge/Project-Page-0099cc"></a>
<a href="https://arxiv.org/abs/2505.01425"><img src="https://img.shields.io/badge/arXiv-2505.01425-b31b1b.svg"></a>
</p>
GEM is a generalist model for human motion that handles multiple tasks with a single model, supporting diverse conditioning signals including video, keypoints, text, audio, and 3D keyframes.
📰 News
- [December 2025] 📢 GENMO has been renamed to GEM.
- [October 2025] 📢 The GEM codebase is released!
Stay tuned for the pretrained models and evaluation scripts.
Follow the project page for updates and announcements.
🚀 Highlights
GEM introduces a unified generative framework that connects motion estimation and generation through shared objectives.
- Unified framework: Reframes motion estimation as constrained generation, allowing a single model to perform both tasks.
- Regression × Diffusion synergy: Combines the accuracy of regression models with the diversity of diffusion-based generation.
- Estimation-guided training: Trains effectively on in-the-wild datasets using only 2D or textual supervision.
- Multimodal conditioning: Supports video, text, audio, 2D/3D keyframes, or even time-varying mixed inputs (e.g., video → text → video).
- Arbitrary-length motion: Generates continuous, coherent sequences of any duration in one diffusion pass.
- State-of-the-art performance: Achieves leading results on diverse motion estimation and generation benchmarks.
For more details, visit the GEM project page →
Pretrained Models
You can download pretrained models from Google Drive.
📖 Paper & Citation
Paper:
GENMO: A GENeralist Model for Human MOtion
Jiefeng Li, Jinkun Cao, Haotian Zhang, Davis Rempe, Jan Kautz, Umar Iqbal, Ye Yuan
ICCV, 2025
BibTeX:
@inproceedings{genmo2025,
title = {GENMO: A GENeralist Model for Human MOtion},
author = {Li, Jiefeng and Cao, Jinkun and Zhang, Haotian and Rempe, Davis and Kautz, Jan and Iqbal, Umar and Yuan, Ye},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
year = {2025}
}
- Created
- Feb 28, 2026
- Updated
- Mar 3, 2026