Search papers, labs, and topics across Lattice.
3
0
7
SIGA transforms general coding agents into efficient operators of scientific simulators, achieving a 36x speedup in setup time compared to human experts.
Transformer-based architectures can now outperform CNNs in multi-view crowd tracking, especially in large, complex real-world scenes, thanks to a novel view-ground interaction mechanism.
Today's best AI agents still fail more than half the time on real-world tasks combining vision, search, and coding, revealing critical gaps in reasoning and tool use.
