Search papers, labs, and topics across Lattice.
3
0
6
Today's best AI agents can only complete 33% of common online tasks like booking appointments or filling out job applications, revealing a significant gap between current capabilities and real-world utility.
Achieve better compression in low-bit quantization by considering not just numerical sensitivity, but also the structural role of each layer.
Train your LLMs and ViTs faster: a nonparametric teaching method cuts training time by up to 21% *without* sacrificing accuracy.
