Views
No views yet
| Component | Detail |
|---|---|
| Base model | Wan2.2-TI2V-5B |
| Text encoder | UMT5-XXL |
| VAE stride | (4, 16, 16) |
| Depth branch layers | 10 |
| Action dim | 14 (dual-arm relative EE pose + gripper) |
| Proprio dim | 16 (dual-arm absolute EE pose + gripper) |
| Prediction horizon | 8 frames video / 32 actions |
| Checkpoint | Path | Description | Training Steps |
|---|---|---|---|
| Pretrained | pretrained/ | Pretrained on 5,800+ hours of cross-embodiment data | 40,000 |
| RoboCasa SFT | robocasa_sft/ | Fine-tuned on RoboCasa (24 kitchen tasks) | 20,000 |
| RoboTwin SFT | robotwin_sft/ | Fine-tuned on RoboTwin 2.0 (50 dual-arm tasks) | 40,000 |
{checkpoint_name}/
├── config.yaml # Training config with normalization statistics
└── checkpoints/
└── last.ckpt # Model weights (~37GB)| Benchmark | Setting | Avg Success Rate |
|---|---|---|
| RoboCasa | 24 kitchen manipulation tasks | 79.2% |
| RoboTwin 2.0 | Clean (50 tasks) | 89.8% |
| RoboTwin 2.0 | Randomized (50 tasks) | 90.7% |
1# Please refer to the code repository for full inference and evaluation scripts:
2# https://github.com/sharinka0715/X-WAM1@article{guo2026xwam,
2 title={Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising},
3 author={Guo, Jun and Li, Qiwei and Li, Peiyan and Chen, Zilong and Sun, Nan and Su, Yifei and Wang, Heyun and Zhang, Yuan and Li, Xinghang and Liu, Huaping},
4 journal={arXiv preprint arXiv:2604.26694},
5 year={2026}
6}