Search papers, labs, and topics across Lattice.
4
0
6
Sub-quadratic linear attention no longer requires full-precision state caching: 8-bit recurrent states can match FP32 accuracy while delivering up to 3.70× kernel speedups without any retraining.
Quantum machine learning enhances Q-matrix estimation by providing greater stability and robustness, even when classical methods achieve higher average accuracy.
ASTELD uncovers a critical gap in the autonomous AI landscape: no evaluated systems achieve both local-first deployment and enterprise-grade security.
Small digit changes can lead to large click misplacements, and MissClick exploits this to achieve unprecedented attack success rates against GUI grounding models.
