--- library_name: lerobot license: apache-2.0 pipeline_tag: robotics base_model: amd/CAE-FastWAM datasets: - yuanty/LIBERO-fastwam tags: - cae_fastwam - lerobot - libero - robotics - world-action-model --- # CAE-FastWAM (LeRobot format) [CAE-FastWAM](https://huggingface.co/amd/CAE-FastWAM) converted to the [LeRobot](https://github.com/huggingface/lerobot) checkpoint format. CAE-FastWAM is a [FastWAM](https://arxiv.org/abs/2603.16666) world action model with a Compact Action Expert: a small (32-wide) action expert denoises latent action tokens, and a LIBERO-suite-conditioned action decoder turns them into the action chunk, on top of FastWAM's Wan2.2-TI2V-5B video expert. The weights are the same as [amd/CAE-FastWAM](https://huggingface.co/amd/CAE-FastWAM); this repo only changes the layout: `config.json` (including the per-suite min/max normalisation statistics, `task_suite_stats`), `model.safetensors`, and FastWAM's standard LeRobot pre/post-processors, which use the statistics of the selected suite. It also carries the frozen action-VAE encoder, so the policy can be fine-tuned with the original CAE-FastWAM objective. ## Installation The `cae_fastwam` policy type is proposed for LeRobot in [huggingface/lerobot#5317](https://github.com/huggingface/lerobot/pull/5317) and is not merged yet. Until then, install LeRobot from the commit used for this checkpoint: ```bash pip install "lerobot[fastwam,libero] @ git+https://github.com/hiteshK03/lerobot.git@e0606546945b93f0cfe87c98918904279dba94ad" ``` Once the PR is merged, install from upstream instead: ```bash pip install "lerobot[fastwam,libero] @ git+https://github.com/huggingface/lerobot.git@main" ``` Inclusion in a LeRobot release is decided by the LeRobot maintainers. The script used to convert the original checkpoint is in [`converter/`](https://huggingface.co/amd/CAE-FastWAM-lerobot/tree/main/converter) (see its [README](https://huggingface.co/amd/CAE-FastWAM-lerobot/blob/main/converter/README.md)). ## Inputs and outputs | Feature | Type | Shape | | --- | --- | --- | | `observation.images.image` (agent view) | visual | (3, 224, 224), resized by the model as in FastWAM | | `observation.images.image2` (wrist view) | visual | (3, 224, 224), resized by the model as in FastWAM | | `observation.state` | state | (8,) | | `action` | action | (7,) | Select the LIBERO suite with `--policy.task_suite` (`libero_spatial`, `libero_object`, `libero_goal` or `libero_10`); evaluate one suite per run. ## Results LIBERO with LeRobot's `lerobot-eval`: bfloat16, 10 denoising steps, 256 x 256 camera frames, seed 42, 50 episodes per task (10 tasks per suite), at most 400 steps per episode (700 for `libero_10`): | Suite | Success rate | Episodes | | --- | ---: | ---: | | libero_spatial | 96.0% (480/500) | 500 | | libero_object | 99.4% (497/500) | 500 | | libero_goal | 94.4% (472/500) | 500 | | libero_10 | 95.8% (479/500) | 500 | | **Average** | **96.4% (1928/2000)** | 2000 | This version processes observations with FastWAM's own path (in-model image resize, LeRobot's standard min/max normaliser). The previous version of this repo, with its own image resize step and normaliser, scored 96.7% (1934/2000) in an earlier run of this protocol. Run side by side on the same 2000 episodes, the previous version scored 96.3% (1926/2000) and this version 96.4%; no task differed significantly. Reproduce (per suite; `--env.episode_length=700` for `libero_10`), on one AMD Instinct MI355X: ```bash lerobot-eval --policy.path=amd/CAE-FastWAM-lerobot --policy.task_suite=libero_spatial \ --env.type=libero --env.task=libero_spatial \ --env.observation_height=256 --env.observation_width=256 --env.episode_length=400 \ --eval.batch_size=5 --eval.n_episodes=50 --seed=42 ``` LIBERO stack: the one pinned by LeRobot's LIBERO benchmark image (hf-libero 0.1.4, robosuite 1.4.0, MuJoCo 3.3.1), CPU physics, OSMesa rendering. The MuJoCo version matters: with MuJoCo 3.8.1 the `libero_spatial` task 5 scene settles differently, and the previous version of this repo scored 94.5% on average under it. Please report the MuJoCo version with LIBERO results. For reference, the [amd/CAE-FastWAM](https://huggingface.co/amd/CAE-FastWAM) card reports 97.28 ± 0.20% with GEAK-optimized inference and a GPU-simulated LIBERO (mean of 11 runs of 2000 episodes). ## Fine-tuning The checkpoint holds the frozen action-VAE encoder and decoder, so `lerobot-train --policy.path=amd/CAE-FastWAM-lerobot --policy.task_suite= --accelerator.mixed_precision=bf16 ...` fine-tunes the video and action experts with the original CAE-FastWAM objective, one suite per run. ## Provenance and license Converted from [amd/CAE-FastWAM](https://huggingface.co/amd/CAE-FastWAM) (Apache-2.0, Advanced Micro Devices, Inc.), a fine-tune of [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B) with the [FastWAM](https://github.com/yuantianyuan01/FastWAM) recipe on LIBERO. See `LICENSE` and `NOTICE`.