Full Professor, University College London
2 papers at NeurIPS 2025
Our proposed RH-Partial2Global adopts a jackknife conformal prediction-guided selection strategy to construct reliable alternative sets and a covering design-based sampling strategy to ensure holistic coverage of local pairwise preferences.
We introduce the warping-and-inpainting strategy to incorporate image inpainting techniques into 3D GAN inversion and propose a novel 3D GAN inversion method, WarpGAN.
