Samba: A Hybrid Mamba Model for Audio-Visual Navigation

Jul 16, 2026

Researchers have introduced Samba, a hybrid Mamba-based model for audio-visual navigation that replaces conventional GRUs with a Mamba State Encoder and incorporates an Audio Mamba Encoder to better capture global time-frequency dependencies. On the Matterport3D dataset, Samba achieves an 11.3% improvement in navigation success rate over state-of-the-art models, with even greater gains reported on the Replica dataset. The model demonstrates strong generalization to unheard sound sources and unseen scenes.

Why it matters: Samba modernizes the core architecture for audio-visual navigation, offering improved performance and efficiency, and sets a new direction for future research in embodied AI navigation.

Full story at: arXiv Machine Learning ↗