Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
7
Cross-modal safety drift can significantly undermine the safety of multimodal language models, but a new method shows how to effectively transfer safety awareness from text to mitigate this risk.
Existing detection systems fail to reliably identify synthetic credibility, with MLLMs achieving only a 10.5% true positive rate under stringent conditions.
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%.
