ResearcharXivNEW

MemoryWAM: Efficient World Action Modeling with Persistent Memory

Yang 2026-06-18
Sizhe YangJuncheng MuTianming Wei

Robust robotic manipulation in the real world requires not only an understanding of the current observation, but also memory and dynamics modeling. World action models (WAMs) possess these capabilities by jointly modeling visual foresight and actions conditioned on both current and historical observations, making them a promising paradigm for robotic manipulation. However, existing WAMs face a fun

Read on arXiv
Data aggregated and editorially reviewed by TrendMing.

Key Contributions

  • Robust robotic manipulation in the real world requires not only an understanding of the current observation, but also memory and dynamics modeling.
  • World action models (WAMs) possess these capabilities by jointly modeling visual foresight and actions conditioned on both current and historical observations, making them a promising paradigm for robotic manipulation.
  • However, existing WAMs face a fun

Research Themes

AIResearch