Xiaomi open-sources MiDashengLM-Spatial audio model
Xiaomi released MiDashengLM-Spatial, an Apache 2.0 audio model built on MiDashengLM-7B with a new Spatial-Dasheng encoder. It combines general audio understanding with sound direction, distance and movement.
First seen 16 Oct, 03:04 UTC on Pandaily1 sourceLast update 6h ago
XiaomiLaunch · 16 Oct
MiDashengLM-Spatial
Open-weight model
Openweights
What the sources say
Linked, never rewritten. Official means the lab itself.
Official0
No word from Xiaomi yet.
How it unfolded
Every source in the order it appeared. Times in UTC.