EasyWAM-MoT-IDM-Wan22

This repository hosts released EasyWAM-MoT-IDM checkpoints built on Wan2.2-TI2V-5B. EasyWAM-MoT-IDM extends the joint dual-DiT design with a teacher-forced conditional-video branch for action prediction. 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

Model	Spatial	Object	Goal	LIBERO-10	Avg.
EasyWAM-Unified	98.4	98.8	99.2	98.0	98.6
EasyWAM-MoT	97.0	99.2	96.6	94.0	96.7
EasyWAM-MoT-Joint	98.2	98.0	97.6	96.8	97.7
🔥 EasyWAM-MoT-IDM	99.0	99.2	98.8	97.4	98.6
EasyWAM-Hidden	99.2	100.0	97.8	98.2	98.8

LoRA (Rank 128)

Model	Spatial	Object	Goal	LIBERO-10	Avg.
EasyWAM-Unified	91.2	98.8	91.8	66.2	87.0
EasyWAM-MoT	96.8	99.6	97.4	90.0	95.9
EasyWAM-Hidden	98.0	99.8	89.4	86.6	93.5

LIBERO-Plus

Model	Background	Camera	Language	Layout	Light	Noise	Robot	Avg.
EasyWAM-Unified	72.3	54.8	93.7	83.4	97.0	72.0	83.4	79.0
EasyWAM-MoT	64.5	45.5	71.4	80.1	94.7	78.5	71.5	71.7
EasyWAM-MoT-Joint	60.9	47.3	89.7	80.5	92.4	68.9	75.9	73.3
🔥 EasyWAM-MoT-IDM	62.2	52.0	94.1	82.0	93.2	67.8	78.0	75.3
EasyWAM-Hidden	59.3	57.0	93.2	84.3	95.0	70.8	83.7	77.6

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-IDM-Wan22 \
  libero_mot_idm_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_idm_wan22 \
  ckpt=./checkpoints/libero_mot_idm_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_idm_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}
}