SCOPE accelerates autoregressive video diffusion up to 4.73x by using a tri-modal cache-predict-recompute scheduler with Taylor extrapolation and selective active-frame computation while preserving output quality.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
CONDITIONAL 2roles
method 1polarities
use method 1representative citing papers
OFA-Diffusion Compression trains diffusion models once to yield multiple size-specific compressed subnetworks via restricted candidate spaces, importance-based channel allocation, and reweighting.
citing papers explorer
-
Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation
SCOPE accelerates autoregressive video diffusion up to 4.73x by using a tri-modal cache-predict-recompute scheduler with Taylor extrapolation and selective active-frame computation while preserving output quality.
-
OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner
OFA-Diffusion Compression trains diffusion models once to yield multiple size-specific compressed subnetworks via restricted candidate spaces, importance-based channel allocation, and reweighting.