WAM-Adapter: Efficiently Adapting Video-DiT World Representations to Robot Actions

Dongxu Liu, Zhe Li, zundong Ke, Zhipeng ZhangOpenReview 2027 · Submission to ICLR 2027 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Pretrained Video Diffusion Transformers encode rich spatiotemporal priors from large-scale videos, making them promising backbones for robot control. However, efficiently adapting them into World Action Models remains challenging. Existing approaches reduce video-adaptation or action-prediction costs, but it remains unclear whether representations produced during future-video adaptation can directly support lightweight action prediction. To address this gap, we propose WAM-Adapter, a parameter- and training-efficient framework that freezes the Video-DiT backbone, adapts it with LoRA, and reuses multi-layer representations for action prediction. A lightweight readout organizes multi-layer K/V representations from current-and-future processing into Current, Early-Future, and Late-Future groups, applying group-specific cross-layer fusion for action-chunk prediction. Inference requires a single Video-DiT forward over the current observation and noisy future slots, without future-video generation or iterative action denoising. Without embodied pretraining, WAM-Adapter uses only 121M trainable parameters with a compact Wan-1.3B backbone, achieving 89.0\% success across 50 RoboTwin~2.0 tasks, 98.5\% on LIBERO, and 75.17\% on LIBERO-Plus. To our knowledge, this is the smallest reported trainable-parameter budget for directly trained WAMs without embodied pretraining. Under the same setting, WAM-Adapter improves training throughput by 9.66$\times$ while using 98\% fewer trainable parameters than Fast-WAM. These results show that Video-DiT representations formed during world-model adaptation can be efficiently reused for strong robot control.
BibTeX
@misc{liu2027wam,
  author = {Dongxu Liu and Zhe Li and zundong Ke and Zhipeng Zhang},
  title = {{WAM-Adapter: Efficiently Adapting Video-DiT World Representations to Robot Actions}},
  year = {2027},
  url = {https://openreview.net/forum?id=pUNarnov3p},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2027},
}

Loading related content...

Figure