Search papers, labs, and topics across Lattice.
3
3
5
3
Safety-aligned LLMs are so consistently risk-averse that a single, transferable "poison" document can now block up to 96% of queries across different RAG systems, even without access to the target model.
Web agents can become significantly more reliable by consulting a world model to simulate the consequences of their actions *before* committing to them.
Even state-of-the-art multimodal LLMs like GPT-5.2 and Claude 4.5 can be jailbroken nearly half the time using OpenRT's diverse suite of attacks, revealing a critical lack of generalization across attack paradigms.
