潛在動作作為意向使世界行動模型能夠實現高效未來想像

摘要

世界動作模型（WAM）透過建模觀測如何演進來改善機器人控制，但在測試時生成未來觀測會帶來可觀的延遲。Fast-WAM 為提升效率而移除此過程；然而，我們匹配的實作顯示，Fast-WAM 的泛化能力低於具未來感知的替代方案，特別是在機器人示範稀少與分布外情境下。為填補此差距，我們提出 **LAWA**，一種 WAM 架構，使用緊湊的潛在動作作為未來意圖的操作性表徵，使其能在不生成未來觀測的情況下，於測試時進行高效的未來想像。具體而言，由無動作預訓練增強的離散分詞器，會產生以操作為中心的碼本目標。LAWA 聯合去噪一個錨定於這些目標的連續潛在狀態與可執行動作片段，同時在推論時省略未來影片分支。在 RoboCasa 上，LAWA 在少樣本與完整資料設定中分別達到 65.6% 與 80.8% 的當前最佳平均成功率，較匹配的 Fast-WAM 基線提升 9.6 與 4.5 個百分點。它也維持與匹配之 Joint-WAM 變體相當的效能水準，同時需要降低 42.9% 的推論延遲。LAWA 亦在 LIBERO-Plus 上展現具競爭力的零樣本穩健性，並在真實世界任務中表現優異。這些結果顯示，未來想像無需被捨棄：以緊湊潛在動作保留它，可在效能、泛化與延遲之間取得有效取捨。程式碼與模型將予以釋出。

English

World action models (WAMs) improve robot control by modeling how observations evolve, but generating future observations at test time incurs substantial latency. Fast-WAM removes this process for efficiency; however, our matched implementations show lower generalization for Fast-WAM than for future-aware alternatives, especially with scarce robot demonstrations and in out-of-distribution scenarios. To bridge this gap, we introduce **LAWA**, a WAM architecture that uses compact latent actions as an operational representation of future intentions, enabling efficient test-time future imagination without generating future observations. Specifically, a discrete tokenizer enhanced by action-free pre-training produces manipulation-centric codebook targets. LAWA jointly denoises a continuous latent state anchored to these targets with executable action chunks while omitting the future-video branch at inference. On RoboCasa, LAWA achieves state-of-the-art average success rates of 65.6% and 80.8% in the few-shot and full data settings, improving over the matched Fast-WAM baseline by 9.6 and 4.5 points, respectively. It also preserves the performance level of the matched Joint-WAM variant while requiring 42.9% lower inference latency. LAWA also demonstrates competitive zero-shot robustness on LIBERO-Plus and superior performance on real-world tasks. These results show that future imagination need not be discarded: retaining it with compact latent actions yields an effective trade-off among performance, generalization, and latency. Code and models will be released.