Newest papers

PrismWAM: Decoupling State Representations in World Action Models

Tianyu Xin, Wanqi Zhong, Bowen Hu, Zhangchi Guo, Lijie Wang, Yiming Wang, Haoran Liao, Heyang Yu, Xiaoyu Tian, Zhiding Yu, Yiming Li · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26564 · cited by 0 works (OpenAlex) · open-access PDF

German

World Action Models (WAMs) repräsentieren in der Regel die Welt durch latente Einbettungen aus vorgefertigten Video-Modellen, die heterogene Aspekte der Welt vorausschneiden, von der Art und Weise, wie sie aussieht (z.B. Textur und Farbe) bis hin zu der physikalischen Konfiguration (z.B. Besatzung und Position). Dies wirft eine unerforschte Frage auf: $\textb{WAM}, die den Zustand eines WAM ausmachen sollte, während wir argumentieren, dass der Weltzustand von der Art und Weise, wie die Welt aussieht (z.B. Textur und Farbe) bis hin zur physikalischen Konfiguration (z.B. Besatzung und Position) getrennt werden sollte: Die erste erfasst den sem

Machine translation (Meta M2M100); the English original follows.

Abstract

World Action Models (WAMs) typically represent the world through latent embeddings from pretrained video models, which entangle heterogeneous aspects of the world, from how it looks (e.g., texture and color) to how it is physically configured (e.g., occupancy and pose). This raises an underexplored question: $\textbf{what should constitute the state of a WAM?}$ We argue that the world state should separate how the world appears from how the world evolves under action: the former captures semantic context, while the latter is governed by physical state. To this end, we propose $\textbf{PrismWAM}$, which decouples physics from semantics while jointly modeling state and action. PrismWAM factorizes an embodied task into a $\mathrm{Semantic\ Planning}\rightarrow\mathrm{Physical\ Rollout}\rightarrow\mathrm{Executable\ Action}$ pipeline: given only the initial RGB observation, semantic planning learns to predict the final goal image, while physical rollout predicts the fine-grained evolution toward this goal in depth space; executable actions are then generated from the depth rollout. Without any embodied action pretraining or additional data augmentation, PrismWAM achieves strong manipulation performance in both simulation and the real world. Notably, PrismWAM even surpasses a broad range of models with large-scale embodied action pretraining (e.g., OpenWAM-$α$). More broadly, we reframe World Action Models from modeling how the world looks to how it responds to action, paving the way for action-centric world models grounded in occupancy, flow, tactile sensing, proprioception, and beyond.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Action (physics), Embodied cognition, Semantics (computer science), Artificial intelligence, Decoupling (probability)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange