QLabs

Researchers at QLabs have published Dust, a method for pretraining transformer models without using backpropagation. The work challenges the fundamental training algorithm underpinning modern AI, and it is drawing attention among machine learning practitioners debating whether such alternatives could ever match gradient-based training at scale.

A research project called Dust claims a method for pretraining transformer models without backpropagation, the algorithm at the core of modern deep learning. If the results hold up, the approach could challenge assumptions about how large models must be trained, but independent verification and details of its performance are not yet established.