Search papers, labs, and topics across Lattice.
2
0
3
Unfolding convolutional kernels breaks Muon's optimization geometry; aligning polar updates with the true convolution operator in the frequency domain cuts flow-matching compute by nearly 40% while radically outperforming Adam.
Learning shared dynamics across heterogeneous systems gets a boost from a new distributionally robust approach that balances information via a worst-case reward optimization.
