OpenMOSS/EasyWAM-MoT-IDM-Cosmos25
Model Introduction
Files & versions
Pull Requests
Discussion
Analysis

EasyWAM-MoT-IDM-Cosmos25

This repository hosts released EasyWAM-MoT-IDM checkpoints built on Cosmos-Predict2.5-2B. 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 Cosmos-Predict2.5-2B backbone are shown together for comparison, and 🔥 marks the architecture released in this repository.

Full-Parameter

ModelSpatialObjectGoalLIBERO-10Avg.
EasyWAM-Unified97.899.497.093.096.8
EasyWAM-MoT98.098.498.495.697.6
EasyWAM-MoT-Joint98.699.898.496.098.2
🔥 EasyWAM-MoT-IDM99.499.499.898.499.3
EasyWAM-Hidden97.298.896.095.096.8

LIBERO-Plus

ModelBackgroundCameraLanguageLayoutLightNoiseRobotAvg.
EasyWAM-Unified72.763.790.182.689.272.179.278.2
EasyWAM-MoT60.775.192.382.692.681.358.577.7
EasyWAM-MoT-Joint62.160.896.684.594.469.476.977.7
🔥 EasyWAM-MoT-IDM66.459.893.885.789.072.381.978.4
EasyWAM-Hidden59.565.992.685.089.168.382.577.8

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-Cosmos25 \
  libero_mot_idm_cosmos25.pt \
  libero_dataset_stats.json \
  --local-dir ./checkpoints

Evaluation

Install EasyWAM, prepare the Cosmos-Predict2.5-2B 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_cosmos25 \
  ckpt=./checkpoints/libero_mot_idm_cosmos25.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_cosmos25.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}
}