Skip to content

Question on 1-Step Inference Logic in DreamZero-Flash #72

@2460707925

Description

@2460707925

During 1-step inference, the input is pure noise and no "noisy image" actually exists yet, meaning the action branch is either guessing blindly or simply relying heavily on historical context. Therefore, have you conducted any ablation studies by completely removing/masking out the current-chunk video prediction branch during 1-step inference? Also, have you considered improving your algorithm using approaches like MeanFlow or Consistency Models to rectify the 1-step vector field?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions