Yang Yue

Robust prediction from corrupted latents, not diffusion objectives, unlocks superior visual tokenizers for diffusion models.

Ambiguous object selection in text-guided image editing is solved by directly annotating the canvas, achieving state-of-the-art performance in complex edits.

World action models do not need to render clean future video to generalize: conditioning on a single forward pass of pure noise captures virtually all the robustness benefits of multi-step diffusion at a fraction of the compute.