Robotics
PyTorch
robot-learning
world-action-model
flow-matching
libero
robocoin
galaxea

RIFT Checkpoints

Checkpoints for Keep the Future, Drop the Rollout: RIFT for World Action Models. Code and evaluation.

Checkpoints

Each dataset has one top-level directory. Model variants live inside that directory.

Dataset Directory Models
LIBERO libero FastWAM; RIFT, FastWAM-IDM and FastWAM-Joint (step 21,700); Cosmos Policy Predict2-2B
RoboCOIN, three tasks robocoin_multitask_mm RIFT (final), 10 epochs / step 9,340
Galaxea indoor cleaning galaxea_indoor_cleaning_3cam224 FastWAM, FastWAM-Joint and RIFT, 10 epochs / step 14,830

Shared Wan VAE, text-encoder, and tokenizer files are under assets/. Exact checkpoint paths, hashes, and source revisions are listed in checkpoint_manifest.json. Use each model's own normalization statistics.

Download

LIBERO Cosmos-2:

hf download PoopBear/RIFT --include 'libero/cosmos-2/*' --local-dir ./checkpoints

LIBERO FastWAM:

hf download PoopBear/RIFT --include 'libero/fastwam/*' --local-dir ./checkpoints

LIBERO RIFT:

hf download PoopBear/RIFT --include 'libero/rift/*' --local-dir ./checkpoints

RoboCOIN RIFT:

hf download PoopBear/RIFT --include 'robocoin_multitask_mm/rift_10ep/*' --local-dir ./checkpoints

Galaxea RIFT:

hf download PoopBear/RIFT --include 'galaxea_indoor_cleaning_3cam224/rift_10ep/*' --local-dir ./checkpoints

The real-world model folders include saved training configurations. LIBERO model configs must be composed with the corresponding task and data configs. Set local dataset and pretrained asset paths for your installation. Load PyTorch checkpoints with weights_only=True.

Citation

@article{zhang2026rift,
  title={Keep the Future, Drop the Rollout: RIFT for World Action Models},
  author={Zhang, Chushan and Tong, Jinguang and Li, Xuesong and Wang, Yikai and Li, Hongdong},
  journal={arXiv preprint arXiv:2608.11521},
  year={2026}
}

License

RIFT checkpoints are distributed under the Apache License 2.0 (see LICENSE). RIFT source code is distributed separately under the MIT License. See NOTICE for attribution.

The third-party Cosmos Policy files in libero/cosmos-2/ retain their original NVIDIA One-Way Noncommercial License (NSCLv1). See the included license and original model card.

Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading

Model tree for PoopBear/RIFT

Finetuned
(100)
this model

Datasets used to train PoopBear/RIFT

Paper for PoopBear/RIFT