Search papers, labs, and topics across Lattice.
University of Sydney
3
0
4
Linear transformers can achieve efficient in-context learning by mapping context distributions to response functions, challenging the traditional softmax approach.
Scaling laws for contrastive learning reveal that learning interactions between views fundamentally alters optimization dynamics compared to linear regression.
Sparsity could be the key to unlocking efficient neural networks for learning operators on infinite-dimensional function spaces, sidestepping the curse of dimensionality.
