Search papers, labs, and topics across Lattice.
3
0
6
0
UI-Mate-27B not only sets a new open-weight benchmark in GUI automation but also doubles the success rate of long-horizon tasks with just one demonstration.
Learnable critics that evaluate the model's own GUI grounding proposals, rather than relying on static geometric heuristics, unlock substantial gains in accuracy.
Web agents can become significantly more reliable by consulting a world model to simulate the consequences of their actions *before* committing to them.
