| title | Light-WAM: Efficient World Action Models with State-Fusion Action Decoding |
|---|---|
| authors | Ziang Li, Dongzhou Cheng, Yibin Wang, Shiyue Wang, Xiaoyang Xu, Lingxuan Weng, Juan Wang, Jiaqi Wang |
| date | 2026-06-06 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.08242 |
| affiliation | Wuhan Univeristy |
| upvotes | 12 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant temporal structure in its representations. Current WAMs often rely on large-scale generative architectures that incur high training costs and inference latency, making them difficult to deploy as efficient closed-loop policies. We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Specifically, it is built with a compact video backbone and performs future-video supervision in a downsampled latent space, reducing the cost of video co-training while retaining its benefits for representation learning. For action prediction, Light-WAM introduces the StateFusionActionExpert, which reads adapted states from multiple backbone layers, fuses them through learned-query pooling, and directly predicts action chunks in a single forward pass. This design provides an efficient interface between video backbone representations and robot actions, avoiding the need for heavy generative action experts. Experiments demonstrate that Light-WAM maintains strong performance on LIBERO and achieves usable multi-task performance on RoboTwin 2.0, while using only 0.44B trainable parameters. It also achieves 72.03ms inference latency with 4.1GiB peak GPU memory and improved training throughput. |
cite
@misc{li2026light,
title={Light-WAM: Efficient World Action Models with State-Fusion Action Decoding},
author={Ziang Li and Dongzhou Cheng and Yibin Wang and Shiyue Wang and Xiaoyang Xu and Lingxuan Weng and Juan Wang and Jiaqi Wang},
year={2026},
eprint={2606.08242},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.08242}
}