Search papers, labs, and topics across Lattice.
4
39
6
13
Memory systems that intelligently filter and prioritize information can drastically improve GUI agent performance, as shown by FocusMem's superior results across multiple benchmarks.
OmniPack achieves a remarkable 98% performance retention with a staggering 83.3% reduction in computational load, revolutionizing token compression for omni-modal models.
Existing models mismanage tool use, but Beacon achieves a balance that enhances performance on complex tasks while preserving accuracy on simpler ones.
Forget scaling laws: a meticulously curated and distilled dataset of 1.4M reasoning problems lets smaller models leapfrog larger, less carefully trained ones.
