Soundless but Not Lost: Persistent Audio-Spatial Memory for Semantic Audio-Visual Navigation
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 15598-15606
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62432007)
- National Natural Science Foundation of China (62272390)
This publication has 22 references indexed in Scilit:
- Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities2025
- OpenNav: Open-World Navigation with Multimodal Large Language Models2025
- Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces2025
- Zero-Shot Object Navigation with Vision-Language Models Reasoning2024
- Towards Learning a Generalist Model for Embodied Navigation2024
- RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation2024
- Semantic Audio-Visual Navigation2021
- SoundSpaces: Audio-Visual Navigation in 3D Environments2020
- Habitat: A Platform for Embodied AI Research2019
- Matterport3D: Learning from RGB-D Data in Indoor Environments2017