---
pretty_name: RIFT Checkpoint
license: apache-2.0
library_name: pytorch
base_model: Wan-AI/Wan2.2-TI2V-5B
datasets:
  - yuanty/LIBERO-fastwam
tags:
  - robotics
  - robot-learning
  - world-action-model
  - flow-matching
  - libero
  - arxiv:2608.11521
---

# RIFT Checkpoint

Official checkpoint for
**[Keep the Future, Drop the Rollout: RIFT for World Action Models](https://arxiv.org/abs/2608.11521)**.

## Project

- Paper: https://arxiv.org/abs/2608.11521
- Code: https://github.com/ChushanZhang/RIFT
- Dataset: https://huggingface.co/datasets/yuanty/LIBERO-fastwam

## Files

```text
rift_step021700.pt
dataset_stats.json
config.yaml
```

- `rift_step021700.pt`: released RIFT checkpoint for LIBERO
- `dataset_stats.json`: normalization statistics used by the checkpoint
- `config.yaml`: model configuration

Keep `dataset_stats.json` with the checkpoint during evaluation.

`rift_step021700.pt` uses PyTorch serialization. Download it only from this
repository and load it with `weights_only=True`.

## Download

```bash
pip install -U huggingface_hub

hf download PoopBear/RIFT \
  rift_step021700.pt \
  dataset_stats.json \
  config.yaml \
  --local-dir ./checkpoints/rift
```

Evaluation commands are provided in the
[RIFT repository](https://github.com/ChushanZhang/RIFT#benchmark-evaluation).

## Citation

```bibtex
@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

The checkpoint is distributed under the Apache License 2.0. RIFT source code
is distributed separately under the MIT License. See `NOTICE` for attribution.