SpatialGPT: Zero-Shot Vision-and-Language Navigation via Spatial CoT over Structured Spatial Memory
Open Access
- 3 November 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 423-435
Abstract
No abstract availableThis publication has 11 references indexed in Scilit:
- Towards Learning a Generalist Model for Embodied Navigation2024
- Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions2024
- Vision-language navigation: a survey and taxonomyNeural Computing and Applications, 2023
- DALL-EVAL: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models2023
- Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation2022
- Visual language navigation: a survey and open challengesArtificial Intelligence Review, 2022
- VLN↻BERT: A Recurrent Vision-and-Language BERT for Navigation2021
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training2020
- Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments2018
- Vector-based navigation using grid-like representations in artificial agentsNature, 2018