--- license: apache-2.0 tags: - robotics - world-action-model - libero - robotwin - robocasa --- # LoopedWAM: Looped World Action Models for Elastic Inference Checkpoints of **LoopedWAM** and **LoopedWAM-E** for LIBERO, RoboTwin 2.0 and RoboCasa-GR1. - Code: [github.com/anhdao69/LoopedWAM](https://github.com/anhdao69/LoopedWAM) - Project page: [anhdao69.github.io/LoopedWAM](https://anhdao69.github.io/LoopedWAM) | Benchmark | LoopedWAM | LoopedWAM-E | |---|---|---| | LIBERO (4 suites) | [`libero/LoopedWAM`](libero/LoopedWAM) | [`libero/LoopedWAM-E`](libero/LoopedWAM-E) | | RoboTwin 2.0 (50 tasks) | [`robotwin50/LoopedWAM`](robotwin50/LoopedWAM) | [`robotwin50/LoopedWAM-E`](robotwin50/LoopedWAM-E) | | RoboCasa-GR1 (24 tabletop tasks) | [`robocasa_gr1/LoopedWAM`](robocasa_gr1/LoopedWAM) | [`robocasa_gr1/LoopedWAM-E`](robocasa_gr1/LoopedWAM-E) | LoopedWAM runs its shared action core K_a = 4 times per denoising step, with N = 10 denoising steps by default. LoopedWAM-E is a single checkpoint, distilled from the LoopedWAM of the same benchmark, that runs any K_a in {1, 2, 4} with any N in {2, 5, 10}, chosen at inference time. ## Files Each folder holds: - `policy.pt`: the FP32 weights (0.58B parameters). The architecture is stored in the checkpoint. A LoopedWAM-E checkpoint also contains its teacher's video expert and loads on its own. - `dataset_stats.json`: the normalization statistics of the actions and the proprioception. All models also use the VAE (`Wan2.1_VAE.pth`) and the T5 text encoder (`models_t5_umt5-xxl-enc-bf16.pth`, `google/umt5-xxl`) of [Wan-AI/Wan2.1-T2V-1.3B](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B). [`SHA256SUMS`](SHA256SUMS) lists the SHA-256 of every file. ## Usage ```bash hf download anhdao69/LoopedWAM --local-dir checkpoints/LoopedWAM hf download Wan-AI/Wan2.1-T2V-1.3B --local-dir checkpoints/Wan2.1-T2V-1.3B # LIBERO, LoopedWAM-E with K_a = 2 action loops and N = 2 denoising steps python experiments/libero/eval_libero.py \ --checkpoint checkpoints/LoopedWAM/libero/LoopedWAM-E/policy.pt \ --action-loops 2 --steps 2 --gpus 0,1,2,3 --out evaluate_results/libero/LoopedWAM-E_k2_n2 ``` The evaluation scripts for all three benchmarks, and the training code, are in the [GitHub repository](https://github.com/anhdao69/LoopedWAM). ## Citation ```bibtex @article{dao2026loopedwam, title = {LoopedWAM: Looped World Action Models for Elastic Inference}, author = {Dao, Anh and Liu, Xinxin and Yu, Hang and Chan Santiago, Jeffrey A. and Shang, Yuzhang}, year = {2026} } ```