行動は1パッチに値する：PatchWAMによる統合的世界-行動モデリング
An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAM
連続行動を固定マッピングでパッチとして表現し、専用の行動ヘッドや専門家なしに単一の生成モデルで視覚予測と行動生成を同時に行うPatchWAMを提案。LIBERO-Plusで91.8%、RoboTwin 2.0で96.12%の成功率を達成。
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: Tianheng Wang, Zhou Xie, Heng Jia, Jianhua Xu, Tong Zhang, Kaicheng Yu
分類: cs.RO
原文アブストラクト
Generative visual models offer a foundation for learning representations of physical dynamics, yet their extension to continuous control raises a fundamental question: do visual prediction and action generation require separate computational pathways? Existing approaches usually introduce trainable action heads or separate action experts to bridge low-dimensional states and high-dimensional visual representations. In this work, we explore whether the visual backbone's existing capacity can also support control when actions are expressed in a compatible representation. Thus, we introduce PatchWAM (Patch World-Action Model), which treats continuous actions as another type of patch through a fixed mapping called Action-as-Patch. This allows a single model to predict both how the robot should move and what the scene may look like afterward. Visual prediction and action generation become parts of the same generative process, without a dedicated action head or separate action expert. Experiments with subsampled training windows show gains over a matched dual-expert control, while benchmark evaluations reach 91.8% success rate on LIBERO-Plus and 96.12% on RoboTwin 2.0 in a full-data setting with additional augmented demonstrations. More broadly, the result suggests that capability need not be added where it can be inherited: the constraint on extending a generative backbone is the interface a new signal is written in, not the capacity to model it.