Hallucinating a CIFAR-10 Classifier
We asked language models to write the weights of a zero-initialized CIFAR-10 ResNet-18 without backpropagation.
Longer write-ups of research and other work, newest first.
Hallucinating a CIFAR-10 Classifier
We asked language models to write the weights of a zero-initialized CIFAR-10 ResNet-18 without backpropagation.
Generator Assisted Mixture of Experts for Feature Acquisition in Batch
An approach to choosing which features to query in a batch under a fixed acquisition budget.