Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation pub.sakana.ai/diffusionblock… What if we didn’t have to hold an entire neural network in memory to train it? Standard neural net training optimizes all parameters jointly. As a result, the memory required during training grows linearly with the depth of the network. In our #ICLR2026 paper, we propose DiffusionBlocks, a principled framework to train networks one block at a time, drastically reducing memory requirements while matching end-to-end performance. With DiffusionBlocks, we split the network into blocks and train them one at a time, so you only need memory for a single block. How? We explicitly assign each block a role: to move the representation a little closer to the target than the block before it did. That role turns out to be precisely what a diffusion model does, step by step. Each block only needs to optimize its own objective and can be trained independently. We validated this across five different architectures: • ViT • DiT • Masked diffusion • Autoregressive transformers • Recurrent-depth transformers In each case, performance is competitive with end-to-end training while using a fraction of the memory. This perspective also extends naturally to recurrent-depth (Looped) transformers, which apply the same network iteratively and normally require expensive backpropagation through time (BPTT). Viewed through DiffusionBlocks, we can replace those multiple iterations with a single forward pass during training. Read our paper and code, to learn more. Paper: arxiv.org/abs/2506.14202 GitHub: github.com/SakanaAI/Diffusio… 🐟

In a heartbreaking and tragic scene, my friend's father was trying to help one of the injured when Israel bombed the area, killing him and everyone else there. He died trying to save others.

In 1947, the UN offered a two-state solution. The Jews said YES. The Arabs said NO. Neighboring Arab countries invaded the young Israel. If you reject peace and start a war, you can’t claim victimhood. History matters. 🇮🇱

This is a hard article to read, but I hope you'll do so. I've spent some time reporting on widespread rape and other sexual violence of Palestinian male and female prisoners by Israeli authorities, and the article is now published. The assault victims were warned not to give speak of what they endured -- they were sometimes told they would be killed or raped if they gave interviews -- but they found the courage to do so. One man described being raped three times in a single day in Israeli prison, the third time after he tried to protest. A young woman said the guards would come in at the beginning of each shift and strip her naked and abuse her. Another reported that she was shown photos of herself being raped and warned they would be released unless she cooperated with Israeli intelligence. Even three children who had been detained told me they had been sexually abused. Look, whatever our position on the Middle East, we should be able to agree on being anti-rape. Sexual assaults were horrific when Israeli women were targeted on Oct. 7, and they're equally horrific when Israeli authorities use them against Palestinians day after day after day. We should be able to find common ground in opposing rape. Here's a gift link to the article: nytimes.com/2026/05/11/opini…