Resistive memory-based neural differential equation solver for score-based diffusion model

While AI-generated content (AIGC) strives to replicate human imagination, current models like score-based diffusion remain slow and energy-intensive. This inefficiency stems from conventional digital computers, where physically separated storage and processing units cause data-transfer bottlenecks, and discrete operations disrupt naturally continuous generation dynamics. Here we show a brain-inspired, analog in-memory computing system that overcomes these limitations. By employing resistive memory, our system integrates storage and computation to act as a time-continuous neural differential equation solver. We experimentally validate our solution with 180 nm resistive memory in-memory computing macros. While maintaining generative quality equivalent to the software baseline, our system accelerated both unconditional and conditional generation tasks, by factors of 69.0 and 116.5, respectively, compared to advanced digital hardware. Furthermore, it reduced energy consumption by 31.5% and 52.0%, respectively. Our approach expands the horizon for hardware solutions in edge computing for generative AI applications. Replicating the human brain’s imaginative ability has long been a core AI goal, yet current systems remain limited in speed and efficiency. Yang et al. present a hardware platform based on resistive memory, enabling high-speed, low-power AI content generation while fully preserving output quality.