Q

We are a research lab working on moonshots in deep learning. We are building new learning algorithms that scale to unimaginable amounts of compute, even with little data, resulting in orders-of-magnitude gains in data efficiency and generalization.

Our investors include Jeff Dean, among many others.

Solving generalization

Approximating Solomonoff Induction

Pretraining data efficiency

NanoGPT Slowrun

13x data efficiency with hyper-epoch pretraining

Scaling laws and new scaling axes

Computational depth is all you need:
towards 107-layer neural nets
(X)

Replacing backprop/gradient descent

Dust: Pretraining transformers
without backpropagation

research@qlabs.sh