The audio side is even more interesting, as it seems they totally got rid of positional embedding are just doing a single linear transform to match the LLM input dimension and that's it.
> Audio: We simplified audio processing even further. We removed the audio encoder entirely and projected the raw audio signal into the same dimensional space as text tokens.
> Audio: We simplified audio processing even further. We removed the audio encoder entirely and projected the raw audio signal into the same dimensional space as text tokens.