Search papers, labs, and topics across Lattice.
Institute for Advanced Research, Great Bay University, Dongguan, Guangdong, China
3
0
3
Non-parametric image inpainting using stochastic dynamics outperforms traditional methods without requiring any neural network training.
GaussFusion not only enhances 3D Gaussian representations but also achieves a remarkable improvement in transferability, outperforming existing methods by notable margins.
AI-generated images betray themselves not by their appearance, but by their *behavior*: they are far more sensitive to small perturbations than real images, revealing a fundamental weakness exploitable for universal detection.
