TLDRocket
Sign in

Sakana AI Introduces DiffusionBlocks, a Block-wise Neural Network Training Method Reducing Memory Requirements

Research publication Provisional 75% confidence first seen

Sakana AI developed DiffusionBlocks, a training method that splits neural networks into independently trained blocks by treating the forward pass as a diffusion model denoising process. The approach significantly reduces memory requirements from linear growth with network depth to memory for a single block while maintaining performance on vision and language models, and was accepted at ICLR 2026.

DiffusionBlocks Error Diffusion Sakana AI

Source coverage

DiffusionBlocks: Training Neural Networks One Block at a Time Sakana AI Sakana AI’s Error Diffusion Trains Dale-Compliant Dual-Stream Networks, Reaching 96.7% MNIST and 61.7% CIFAR-10 Without Backpropagation MarkTechPost

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.