Audio MLLMs

Audio MLLMs, developed by various teams like Moonshot AI for Kimi-Audio, are large language models specialized for audio tasks, integrating understanding, generation, and conversation through efficient single-stage training.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.