← Search

Paribesh Regmi

2 accepted papers

2026

Shortcut Diffusion Training with Cumulative Consistency Loss: An Optimal Control View

ICLR 2026poster

Although iterative denoising (i.e., diffusion/flow) methods offer strong generative performance, they suffer from low generation efficiency, requiring hundreds of steps of network forward passes to simulate a single sample. Mitigating this requires taking larger step-sizes during simulation, thereby…

Cited by 0SourcecodeScholar