SR-VLN: Implicit Spatial Reasoning Vision-and-Language Navigation
Vision-and-language navigation (VLN) traditionally relies on explicit reasoning chains, which, despite being interpretable, impose severe constraints on inference efficiency and scalability in long-range environments. Existing multimodal large language models (MLLMs) frequently encounter latency bot...
Shranjeno v:
| Principais autores: | , , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
MDPI AG
2026-06-01
|
| Serija: | Sensors |
| Teme: | |
| Online dostop: | https://www.mdpi.com/1424-8220/26/12/3809 |
| Oznake: |
Brez oznak, prvi označite!
|