Search papers, labs, and topics across Lattice.
3
0
5
3
A black-box defense that reduces harmful outputs in text-to-image models by 37.7% without needing any model retraining or internal access.
EgoPlay achieves a remarkable 17.7% improvement in editing quality over the previous state-of-the-art, redefining the capabilities of egocentric video editing.
VLMs' safety judgments are easily manipulated by simple semantic cues, revealing a reliance on superficial associations rather than true visual understanding.
