必要なときに夢を見る:適応的マルチモーダル推論による世界行動モデルの進化
Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning
世界行動モデル(WAM)の性能を高めるため、タスクの切り替え時にはテキスト推論、細かい操作時には視覚推論を動的に切り替える軽量ルータを導入したAdaWAMを提案した。シミュレーションと実世界のタスクで効率と性能が向上した。
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: Yinzhou Tang, Jingbo Xu, Yu Shang, Zihao Song, Chen Gao, Wei Wu, Yong Li
分類: cs.RO
原文アブストラクト
World Action Models (WAMs) offer a promising approach to embodied intelligence, yet existing methods rely heavily on video prediction as action priors and lack adaptive multimodal reasoning, limiting their effectiveness on long-horizon, complex tasks. We observe that WAMs require different multimodal reasoning modes under different execution contexts: textual reasoning is essential during task transitions to guide high-level action prediction, while visual reasoning is critical during fine-grained manipulation for precise control. Motivated by this observation, we propose \textbf{AdaWAM}, a world action model with adaptive multimodal reasoning abilities. AdaWAM integrates a lightweight dynamic router that autonomously triggers textual or visual reasoning as needed during task execution. Experiments on both simulated and real-world embodied tasks show that AdaWAM substantially improves inference efficiency while outperforming state-of-the-art embodied policies. Codes and demos are available at: https://adawam.github.io/.
