Search papers, labs, and topics across Lattice.
3
0
6
Forget memorizing manipulation artifacts: comparing against a reference library of authentic examples lets you spot forgeries and adapt to new domains without retraining.
Concept erasure in text-to-video diffusion models is far more effective when targeted at specific layers where concepts are naturally more separable from other information.
Existing deepfake detectors fall apart when faced with realistic, multi-step editing pipelines, highlighting the need for methods that can trace the *history* of manipulations, not just detect a single forgery.
