Search papers, labs, and topics across Lattice.
2
0
5
0
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.
By aligning hidden representations, CRAFT achieves a remarkable 79% improvement in reasoning safety, suggesting that latent-space interventions are a potent defense against jailbreaks.
