Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
Paper • 2606.08242 • Published • 10
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Light-WAM Checkpoints
This repository contains released checkpoints for Light-WAM: Efficient World Action Models with State-Fusion Action Decoding.
Contents
Released checkpoints:
lightwam_libero_spatial/lightwam_libero_object/lightwam_libero_goal/lightwam_libero_10/lightwam_robotwin/
Each released model directory follows:
lightwam-checkpoints/<task_name>/
├── config.yaml
├── dataset_stats.json
└── checkpoints/
└── weights/
└── step_xxxxxx.pt
Download
Install the Hugging Face Hub CLI:
pip install -U huggingface_hub
Download all Light-WAM checkpoints:
hf download l1ziang/lightwam-checkpoints \
--local-dir lightwam-checkpoints
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support