Search papers, labs, and topics across Lattice.
5
0
7
0
Achieving a 12.1% boost in robust concept removal, MapRoute++ redefines the boundaries of visual concept unlearning.
OPIUM reveals that harmful side effects of activation steering can be mitigated directly in activation space, enhancing model safety while preserving utility.
Existing explainability methods misrepresent multimodal decision-making, often conflating genuine reasoning with shallow shortcuts.
LLMs can be six times more biased when demographic identity is conveyed implicitly through cultural cues, even when explicit biases are suppressed.
Forget scaling laws: the *structure* of your AI governance system matters more than the specific LLM when it comes to preventing corruption.
