Megadose AI progress, ranked and analyzed.

Thinking with Looped Flows

· ArXiv · AI/CL/LG ·
The paper proposes “looped flows,” a training and inference method for recurrent looped models that aims to make extra test-time computation useful.

The approach trains recurrent updates with local denoising objectives, using decreasing noise levels and shared noise to carry computation across steps. At inference, it integrates a probability-flow velocity from the learned denoiser while maintaining recurrent state. The authors report gains across six reasoning benchmarks, including 58.8% test accuracy on ARC-AGI-1 and 12.2% on ARC-AGI-2. ArXiv · AI/CL/LG's note

score 5

Categories: Research