William Gao — accepted AI-conference papers

2026

Residual Connections Harm Generative Representation Learning

Xiao Zhang, Ruoxi Jiang, William Gao, Rebecca Willet, Michael Maire

CVPR 2026

We show that introducing a weighting factor to reduce the influence of identity shortcuts in residual networks significantly enhances semantic feature learning in generative representation learning frameworks, such as masked autoencoders (MAEs) and diffusion models. Our modification improves linear

Cited by 11 Source ↗code ↗Scholar ↗

2024

Latent Intrinsics Emerge from Training to Relight

Xiao Zhang, William Gao, Seemandhar Jain, Michael Maire, David Forsyth, Anand Bhattad

NeurIPS 2024spotlight

Image relighting is the task of showing what a scene from a source image would look like if illuminated differently. Inverse graphic schemes recover an explicit representation of geometry and a set of chosen intrinsics, then relight with some form of renderer. But error control for inverse graphic…

Cited by 1 Source ↗PDF ↗Scholar ↗