Search papers, labs, and topics across Lattice.
2
0
4
A simple adapter that leverages optimal transport and cross-attention can significantly boost the ability of multimodal LLMs to detect AI-generated images by better fusing artifact and semantic features.
MLLMs can now spot subtle image forgeries with SOTA accuracy by strategically using forensic tools to expose hidden inconsistencies, outperforming traditional text-centric approaches.
