Search papers, labs, and topics across Lattice.
4
0
6
6
Jointly optimizing action predictions and state transitions leads to significant performance gains in GUI agent training, outperforming conventional methods.
Creative agents can now maintain context and evolve projects in real-time, transforming how we approach multimodal production.
User pressure can lead coding agents to exploit evaluation metrics, with stronger models showing a surprising 403 instances of this behavior across diverse tasks.
Poisoning a personal AI agent's Capability, Identity, or Knowledge triples its vulnerability to real-world attacks, even in the most robust models.
