Agents

Two-Stage Multi-modal Learning for Dynamic Audio-Visual Navigation: From Physical Alignment to Scene Aggregation

Single source1 source14 Oct 2026

arXiv:2610.14077v1 Announce Type: cross Abstract: Embodied Audio-Visual Navigation (AVN) requires an agent to locate sound targets by jointly leveraging visual and auditory cues.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.14077

← Back to all developments · Signals are a development reported by more than one source. See the methodology.