Search papers, labs, and topics across Lattice.
University of Chinese Academy of Sciences
2
0
4
Training long-context sparse attention models doesn't have to be a slow, imbalanced mess: SparseBalance achieves 1.33x speedup while *improving* accuracy.
Invariant models can match the accuracy of equivariant machine learning interatomic potentials at a fraction of the computational cost, thanks to a novel attention mechanism.
