一作ACL 2026Poster· Natural Language Processing
VLN - MME : Diagnosing MLLM s as Language-guided Visual Navigation Agents
Xunyi Zhao · Gengze Zhou · Qi Wu
摘要
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a wide range of vision-language tasks. However, their performance as embodied agents, which requires multi-round interaction with spatial reasoning and sequential action prediction, needs further exploration...