Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation 文章

ArXiv CS.CV2026-06-05NEWSen作者: Haocheng Luo, Jiahui Liu, Ruicheng Zhang, Zhizhou Zhong, Jiaqi Huang, Zunnan Xu, Quan Shi, Jun Zhou, Xiu Li
查看原文 →
关系图谱

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation · 相关技术

相关技术

self-distillationperception-reasoning modality gapvisual spatial planningVision-Language ModelsMGSD