AI Paper Atlas

Research map / Video / Video generation

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks

Bhishma Dedhia, David Bourgin, Krishna Kumar Singh, Yuheng Li, Yan Kang, Zhan Xu, Niraj K. Jha, Yuchen Liu

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add global tokens (ablation)VIN-DiT · VIN ablationMAWE: 1.69 -> 1.09Improved
add global tokens (ablation)VIN-DiT · VIN ablationScene cuts: 0.33 -> 0.21Improved
use early token fusion instead of no fusion (ablation)VIN-DiT · VIN ablationScene cuts: 1.00 -> 0.21Improved
use early token fusion instead of no fusion (ablation)VIN-DiT · VIN ablationMAWE: 1.13 -> 1.09Improved
use early fusion instead of late fusion (ablation)VIN-DiT · VIN ablationMAWE: 1.22 -> 1.09Improved
use early fusion instead of mid fusion (ablation)VIN-DiT · VIN ablationScene cuts: 0.33 -> 0.21Improved
expand local frames at inference to 12 from 8 (ablation)VIN-DiT · VIN ablationMAWE: 1.51 -> 1.09Improved
expand local frames at inference to 12 from 10 (ablation)VIN-DiT · VIN ablationMAWE: 1.17 -> 1.09Improved
sample keyframes more densely (0.2s instead of 1.0s) (ablation)VIN-DiT · VIN ablationMAWE: 1.09 -> 1.21No clear effect
use VIN parallel generation instead of full attentionVIN-DiT · 256-frame VBenchDynamic degree: 68.15% -> 87.32%Improved
use VIN instead of full attention on efficiencyVIN-DiT · Efficiency analysisFLOPs: 25-40% fewer FLOPsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy