SOURCE-LINKED INTELLIGENCE

Thinking with Looped Flows

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Humans and machines often solve harder problems by spending more time on computation. In deep learning, looped models implement this idea during inference by recurrently updating a hidden state. In practice, however, their training backpropagates through only one or a few updates, making it hard to train early updates to support future ones. We propose looped flows, an approach that sidesteps this issue by training the recurrence with local denoising objectives. By imposing temporal association across denoising objectives through progressively decreasing noise levels and shared noise, the mode

Read original source ↗ Open in workspace

recordType

paper

region

Global