CA-VLN: Collaborative Agents in MLLM-Powered Visual-Language Navigation

Generalization to unseen environments remains a fundamental challenge in Vision-Language Navigation. To tackle this issue, we propose a novel framework that leverages world knowledge embedded within Multimodal Large Language Models. We introduce Collaborative Agents in Visual-Language Navigation (CA...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Ruolin Zhu, Shaobin Li, Zixing Zhu, Jing Jia, Min Yang
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	MDPI AG 2026-02-01
Цуврал:	Sensors
Нөхцлүүд:	multimodal feature fusion world knowledge episodic memory hierarchical history
Онлайн хандалт:	https://www.mdpi.com/1424-8220/26/4/1254
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!