Search papers, labs, and topics across Lattice.
3
0
5
Turing-20B-A2B achieves exceptional long-context capabilities with only a fraction of its parameters activated, pushing the boundaries of efficiency in physical AI applications.
TuringViT outperforms leading ViT models with just 10% of the training data, making state-of-the-art vision technology accessible to a wider audience.
Jointly optimizing dimensionality reduction and clustering on a manifold yields state-of-the-art clustering performance, even surpassing established algorithms.
