Search papers, labs, and topics across Lattice.
2
0
4
AEGIS achieves near-zero attack success rates against visual synonym jailbreaks while preserving the fidelity of benign outputs, reshaping the defense landscape for text-to-image models.
Forget user-provided forget sets: MAGE lets you unlearn LLM memorization with just a lightweight "anchor," achieving performance on par with corpus-dependent methods.
