GenMimic (wip)
Implementation of GenMimic, From Generated Human Videos to Physically Plausible Robot Trajectories, in Pytorch
GenMimic is a physics-aware reinforcement learning policy conditioned on 3D keypoints, trained with symmetry regularization and keypoint-weighted tracking rewards, allowing humanoids to mimic human actions from noisy, generated videos in a zero-shot manner.
Install
$ pip install genmimic-pytorch
Usage
import torch
from genmimic_pytorch import GenMimic
model = GenMimic()
Citations
@misc{ni2025generatedhumanvideosphysically,
title = {From Generated Human Videos to Physically Plausible Robot Trajectories},
author = {James Ni and Zekai Wang and Wei Lin and Amir Bar and Yann LeCun and Trevor Darrell and Jitendra Malik and Roei Herzig},
year = {2025},
eprint = {2512.05094},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2512.05094},
}
1 maintainer
Metadata
1 maintainer
Release files for genmimic-pytorch 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| genmimic_pytorch-0.0.1.tar.gz | 4.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| genmimic_pytorch-0.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.2 kB
Release files / genmimic_pytorch-0.0.1.tar.gz
| Download URL | genmimic_pytorch-0.0.1.tar.gz |
|---|---|
| Size | 4.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c3d0d550653e4fe441290ee7dd4be6ed9ec9e2331f016dd4dd1dc56856684847
|
|
BLAKE2b-256 checksum How to use checksums |
4c4af8f18bebde01a1d378d22d23c785b23341880fbc9640b8bcd2eef3e20f71
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.17
|
Release files / genmimic_pytorch-0.0.1-py3-none-any.whl
| Download URL | genmimic_pytorch-0.0.1-py3-none-any.whl |
|---|---|
| Size | 3.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6c3e9d663b1fc54c506d79f14ef37713f19b0d2b1a5d7703ba5ca5b42332a64c
|
|
BLAKE2b-256 checksum How to use checksums |
872720cd2b68fe0143d51acb8ccb45c4a583ab33c4a99acbd30fcca39bee6cdd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.17
|
