EasyWAM-MoT-Wan22

EasyWAM-MoT-Wan22

This repository hosts released EasyWAM-MoT checkpoints built on Wan2.2-TI2V-5B. EasyWAM-MoT uses separate Video DiT and Action DiT experts whose tokens interact through mixed self-attention. At inference time, it predicts actions without generating future video. The checkpoints are trained with the EasyWAM codebase.

The LoRA checkpoint uses rank 128 (alpha 128) on the backbone Video DiT target modules. Other trainable EasyWAM modules are stored in the same checkpoint, so it must be loaded with the matching _lora task recipe.

LoRA requirement: The LoRA checkpoint does not include the complete Wan2.2 backbone. Before loading or evaluating it, download the required backbone weights and configure their paths as described in the EasyWAM Wan2.2 backbone guide.

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

LoRA (Rank 128)

LIBERO-Plus

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-Wan22 \
  libero_mot_wan22.pt \
  libero_mot_wan22_lora_128.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_wan22 \
  ckpt=./checkpoints/libero_mot_wan22.pt \
  EVALUATION.dataset_stats_path=./checkpoints/libero_dataset_stats.json

# LoRA checkpoint
python experiments/libero/run_libero_manager.py \
  task=libero_easywam_mot_wan22_lora \
  ckpt=./checkpoints/libero_mot_wan22_lora_128.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_wan22.pt
• LIBERO LoRA checkpoint: libero_mot_wan22_lora_128.pt (rank 128, alpha 128)
• 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}
}