Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching 文章

ArXiv CS.CV2026-06-03NEWSen作者: Hao Zhong, Muzhi Zhu, Shenyan Zeng, Anzhou Li, Cong Chen, Hua Geng, Duochao Shi, Wentao Ye, Tao Lin, Hao Chen, Chunhua Shen
查看原文 →
关系图谱

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching · 相关技术

相关技术

Multimodal Large Language Models (MLLMs)Wide-baseline matching