Sonic-AMG: Streaming Human Motion Generation from Spatial Audio
We present Sonic-AMG, to our knowledge the first framework for streaming human motion generation from spatial audio.
ProofPaper ↗
Key points
- Modeling human reactions to spatial audio requires understanding both what is heard and where it comes from.
- Prior work generates motion offline from complete acoustic and spatial input sequences.
- To reduce this history discrepancy, we introduce rehearsal training, which combines full-sequence teacher-forced supervision with supervised prediction along short autoregressive self-rollouts.
- To keep spatial conditioning consistent with generated motion, we propose spatial feedback, which recomputes body-relative source locations from generated root poses during both rehearsal training and inference.
Sources (1)
- [1]Sonic-AMG: Streaming Human Motion Generation from Spatial AudioarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 09:47 AM
We present Sonic-AMG, to our knowledge the first framework for streaming human motion generation from spatial audio.
Modeling human reactions to spatial audio requires understanding both what is heard and where it comes from.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
- Oct 9, 2026Learning Representations to Guide Pixel Diffusion Transformers
- Oct 8, 2026LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
- Oct 8, 2026One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
- Oct 8, 2026Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
