Thermodynamic Diffusion Inference with Minimal Digital Conditioning
📰 ArXiv cs.AI
arXiv:2604.14332v1 Announce Type: cross Abstract: Diffusion-model inference and overdamped Langevin dynamics are formally identical. A physical substrate that encodes the score function therefore equilibrates to the correct output by thermodynamics alone, requiring no digital arithmetic during inference and potentially achieving a $10{,}000\times$ reduction in energy relative to a GPU. Two fundamental barriers have until now prevented this equivalence from being realized at production scale: non
DeepCamp AI