Search papers, labs, and topics across Lattice.
4
0
6
2
MemCatalyst reveals that targeted data poisoning can drastically boost membership inference accuracy in Vision-Language Models with minimal resource expenditure.
Identity drift in generative agents reveals that anti-self-deception is a dominant modification behavior, challenging assumptions about agent fidelity under pressure.
Simulating 8.3 billion diverse personas reveals nuanced user interactions that traditional evaluations miss, transforming how we assess AI systems.
Explicitly invoking external image tools in vision-language models dramatically reduces jailbreak success rates, even when the tool's output is overridden or unsafe.
