Search papers, labs, and topics across Lattice.
The University of Sydney
4
0
4
Exact boundary enforcement in PINNs isn't enough; the choice of distance function can make or break the accuracy of solutions to elliptic Dirichlet problems.
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.
