OpenMOSS/EasyWAM-MoT-Joint-Wan22
Model Introduction
Files & versions
Pull Requests
Discussion
Analysis

EasyWAM-MoT-Joint-Wan22

This repository hosts released EasyWAM-MoT-Joint checkpoints built on Wan2.2-TI2V-5B. EasyWAM-MoT-Joint uses separate Video DiT and Action DiT experts with mixed self-attention, jointly denoising future-video and action tokens. The checkpoints are trained with the EasyWAM codebase.

LIBERO

Results

Task success rate (%) under the EasyWAM LIBERO evaluation protocol. All results use state_position: sequence; higher is better. Models using the same Wan2.2-TI2V-5B backbone are shown together for comparison, and 🔥 marks the architecture released in this repository.

Full-Parameter

ModelSpatialObjectGoalLIBERO-10Avg.
EasyWAM-Unified98.498.899.298.098.6
EasyWAM-MoT97.099.296.694.096.7
🔥 EasyWAM-MoT-Joint98.298.097.696.897.7
EasyWAM-MoT-IDM99.099.298.897.498.6
EasyWAM-Hidden99.2100.097.898.298.8

LoRA (Rank 128)

ModelSpatialObjectGoalLIBERO-10Avg.
EasyWAM-Unified91.298.891.866.287.0
EasyWAM-MoT96.899.697.490.095.9
EasyWAM-Hidden98.099.889.486.693.5

LIBERO-Plus

ModelBackgroundCameraLanguageLayoutLightNoiseRobotAvg.
EasyWAM-Unified72.354.893.783.497.072.083.479.0
EasyWAM-MoT64.545.571.480.194.778.571.571.7
🔥 EasyWAM-MoT-Joint60.947.389.780.592.468.975.973.3
EasyWAM-MoT-IDM62.252.094.182.093.267.878.075.3
EasyWAM-Hidden59.357.093.284.395.070.883.777.6

LIBERO-Plus results are reported for full-parameter checkpoints only. See the complete EasyWAM benchmark table for source results and comparisons across backbones.

Download

hf download OpenMOSS-Team/EasyWAM-MoT-Joint-Wan22 \
  libero_mot_joint_wan22.pt \
  libero_dataset_stats.json \
  --local-dir ./checkpoints

Evaluation

Install EasyWAM, prepare the Wan2.2-TI2V-5B dependencies using the backbone guide, and set up the simulator using the LIBERO evaluation guide. Then run:

# Full-parameter checkpoint
python experiments/libero/run_libero_manager.py \
  task=libero_easywam_mot_joint_wan22 \
  ckpt=./checkpoints/libero_mot_joint_wan22.pt \
  EVALUATION.dataset_stats_path=./checkpoints/libero_dataset_stats.json

The default protocol evaluates all four LIBERO suites with 50 trials per task. Add MULTIRUN.num_gpus=<gpu-count> to distribute evaluation across multiple GPUs.

Available Checkpoints

  • LIBERO full-parameter checkpoint: libero_mot_joint_wan22.pt
  • LIBERO normalization statistics: libero_dataset_stats.json
  • State-token placement: sequence
  • Checkpoint format: EasyWAM PyTorch checkpoint (.pt)

Project

  • Project page: http://openmoss.ai/EasyWAM/
  • Code: https://github.com/OpenMOSS/EasyWAM

License and Citation

EasyWAM code is released under the MIT License. Released checkpoints in this repository use CC BY-NC 4.0 and remain subject to the terms of their base models and training data. If EasyWAM is useful in your research, please cite:

@misc{easywam2026,
  title  = {EasyWAM: A Unified and Efficient Framework for Training and Evaluating World Action Models},
  author = {EasyWAM-Team},
  year   = {2026},
  url    = {https://github.com/OpenMOSS/EasyWAM}
}