Search papers, labs, and topics across Lattice.
University of Electronic Science and Technology of China
5
0
7
13
LEGO's modular design lets you detect deepfakes with 10x less training data and far fewer epochs, all by focusing on the unique fingerprints of each image generator.
Even without retraining, a simple dual-system approach can significantly boost the performance of self-supervised talking head forgery detectors by refining the ordering of uncertain samples.
Simple frequency masking and gated injection can dramatically improve the generalization of AI-generated image detectors, even against unseen generative models.
Existing synthetic image detectors fail to generalize because they're trained on biased data, but HiMix overcomes this with artifact-aware representations and mixup augmentation, achieving state-of-the-art generalization to unseen generators.
Achieve >95% forget quality in LLMs with minimal side effects by isolating and unlearning tokens within target subdomains using asymmetric LoRA.
