Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation

作者：作者信息待提取 · 单位：University of Washington, National University of Singapore, Microsoft Research, Carnegie Mellon University, horizons. Extensive experiments on four challenging benchmarks (Go Stanford, ReCon, SCAND · 来源：World Models for Embodied AI · 发布日期：2025 · 分类：3. World Models for Navigation