Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
3
Linear attention's recurrent state can be compressed down to 4 bits while outperforming uniform INT8 once precision is dynamically allocated to long-lived memory tracks and output-sensitive key rows.
PILL achieves up to 6.0 BLEU-2 improvement on text infilling while running 1.82x faster than the best existing method, revolutionizing efficiency in diffusion language models.