MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation
Large vision-language models (LVLMs) have shown strong potential for embodied vision-language navigation (VLN), yet their performance degrades on long-horizon trajectories due to context-length limits, redundant historical observations, and unstable spatial alignment across time. These issues make it difficult to both...
Xu-Ya Wei, Yi-Fei Wang, De-Lun Li et al.
· 0 citations