SOURCE-LINKED INTELLIGENCE

LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Vision-Language Navigation (VLN) requires an embodied agent to follow natural-language instructions in unseen environments. Recent progress has been largely driven by Multimodal Large Language Models (MLLMs). Existing methods follow a next-step action prediction paradigm, supervising only the expert action, which requires a high quantity of data for training. They also rely on cognitive maps, accumulated historical frames, or external 3D tools to maintain states, leading to high computational and memory overhead. To realize resource efficiency VLN, we propose LookStep, a unified end-to-end fra

Read original source ↗ Open in workspace

recordType

paper

region

Global