Large-scale object acoustics used to fit generative models of impact sounds
JoshHMcDermott · x · 2026-11-10
Part 8 of McDermott's thread: the team fit probabilistic generative models to large-scale measurements of everyday object acoustics, enabling realistic impact sounds to be sampled given physical variables. The framework separately models impact force and the object's impulse response, combining them to synthesize impact sounds.
More from Research
- ProtoMotions Deployment Stack: One Exported Graph, 1.3 ms C++ Loop for Real Robots — carlosdponx · 2026-11-11
- DeepMind's MKA benchmark splits frontier agents: 95-97% on basics, 28-57% on hard tasks — ArtificialAnlys · 2026-11-11
- MKA deep dive: top models cluster at 95-97% on basics but split 28-57% on hard tasks — ArtificialAnlys · 2026-11-11
- MKA Benchmark by Output Type: No Model Tops 52% on Word or Text Files — ArtificialAnlys · 2026-11-11
- DeepMind-backed MKA benchmark crowns Claude Fable 5.2 at 57%, with 30x cost spread — ArtificialAnlys · 2026-11-11
- Emergent misalignment is predictable OOD; later-layer fine-tuning reduces transfer — AdtRaghunathan · 2026-11-11