Team Ai
Modelpublic

xpeng-robotics/DIAL_checkpoints

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
2likes13downloads
Model Card

DIAL Checkpoints

<p align="center"> <a href="https://xpeng-robotics.github.io/dial/"><b>Project Page</b></a> &nbsp;|&nbsp; <a href="https://xpeng-robotics.github.io/dial/DIAL.pdf"><b>Paper</b></a> &nbsp;|&nbsp; <a href="https://github.com/xpeng-robotics/DIAL"><b>Code</b></a> </p>

Model weights for DIAL (Decoupling Intent and Action via Latent World Modeling), an end-to-end Vision-Language-Action (VLA) framework built on NVIDIA Isaac GR00T N1.5 with a Qwen2.5-VL-3B-Instruct backbone.

Available Checkpoints

CheckpointTraining DataStepsDescription
DIAL-3B-fewshotEgoDex human data + 10% GR1 simulation data20K per stage (3-stage)Co-trained with heterogeneous human demonstrations
DIAL-3B-fulldataAll GR1 simulation data (~24,000 demos)40K per stage (2-stage)Trained on full teleoperation trajectories in simulation

For installation, training, and evaluation instructions, please refer to the GitHub repository.