AMBIT generates and edits first-order ambisonics with executable plans
A shared Transfusion model plans scenes, renders FOA audio, and self-distills on student prefixes.
5 stories, newest first · one card per story
A shared Transfusion model plans scenes, renders FOA audio, and self-distills on student prefixes.
WorldSonus adds real-time, controllable spatial stereo audio to interactive world-model video streams.
WorldSonus adds real-time, controllable spatial audio to silent world models with streaming diffusion.
HelixWorld is a real-time audio-visual world model running joint rollouts at 24 FPS.
OmniEcho benchmarks spatial audio for embodied agents and reports strong perception and navigation results.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views