Faster-WAM: 世界行動モデルに深い行動モジュールは必要か？
Faster-WAM: Do World Action Models Need Deep Action Modules?
ビデオ世界モデルと行動予測を組み合わせた世界行動モデル（WAM）において、行動モジュールの深さをビデオバックボーンから切り離し、軽量な単層ヘッドをドッキングする設計（DoT）を提案。推論速度を3.2倍高速化しつつ、性能と汎化を維持した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Liheng Ma, Rui Heng Yang, Zhanguang Zhang, Mateo Clemente, Ziwen Hu, Tongtong Cao, Yingxue Zhang
分類: cs.AI, cs.LG, cs.RO
原文アブストラクト
World Action Models (WAMs) couple robot action prediction with video world models. Existing WAMs with shared-backbone and Mixture-of-Transformers designs generally tie the depth of the action module to that of the video backbone, resulting in substantial computational overhead and high inference latency. To address this limitation, we introduce Dock of Transformer (DoT), a video-centric design principle that treats a pretrained video Transformer as a representation hub and connects lightweight output-heads through docking interfaces. This enables flexible output-head design while providing direct access to representations from all layers of the backbone. We then introduce \textbf{Faster-WAM}, an instantiation of DoT for WAMs, which docks a single-layer action head onto a 30-layer video backbone. The docking interface fuses keys and values from all video layers and applies RoPE realignment. Without additional embodied pretraining, Faster-WAM achieves competitive performance on LIBERO and RoboTwin 2.0 while demonstrating strong out-of-distribution generalization on LIBERO-Plus. Faster-WAM also achieves the lowest end-to-end latency in our controlled comparison, requiring only 66.5 ms per inference --- a \(3.2\times\) speedup over Fast-WAM. Overall, these results demonstrate that the video-centric DoT architecture supports flexible task-specific head design while delivering low inference latency, strong action-prediction performance, and robust generalization.