Search papers, labs, and topics across Lattice.
3
12
5
6
AgentDoG 1.5 proves you can achieve GPT-5.4-level agent safety with open-source models trained on just 1k samples, slashing deployment overhead by two orders of magnitude.
LLM safety crumbles in low-resource languages because alignment is skin-deep; LASA fixes this by injecting safety at the semantic core, slashing attack success by 88%.
LLMs can move beyond simple refusals to actively guide vulnerable users towards safe outcomes, achieving state-of-the-art safety and robustness against jailbreaks.
