Search papers, labs, and topics across Lattice.
2
0
5
0
On-device LLM inference can be sped up by an order of magnitude with a flexible TrustZone-based system that selectively protects memory and the NPU.
CaTok achieves state-of-the-art ImageNet reconstruction with fewer training epochs by learning causal 1D image representations, outperforming existing visual tokenizers.
