AI Paper Atlas

Research map / Video / Video generation

FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis

Sungwoong Yune, Suheon Jeong, Joo-Young Kim

ECCV 2026 · Video › Video generation · approach: Autoregressive long video generation · 3 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 spatiotemporal token pruning with partial update (20/30/40/70%)InfinityStar · T2V 720pend-to-end latency / speedup: 81.7 s baseline -> 2.01x speedupImproved
spatiotemporal pruning instead of image-based reduction (SparseVAR, FastVAR, ToMe)InfinityStar · T2V 720pPSNR: FastSTAR 28.29 (highest) vs baselines lower; baselines speedup 1.44x-1.76xImproved
apply FastSTAR to image-to-videoInfinityStar · I2V 720pPSNR: 25.65 (best among reduction methods)Improved
add temporal similarity to spatial-only pruning (ablation)FastSTAR · T2Vquality metricsImproved
use random pruning instead of similarity-based pruning (ablation)FastSTAR · T2Vquality metricsHurt
norm degree p=2 vs p=1 or infinity in score fusion (ablation)FastSTAR · T2VSSIM / LPIPSImproved
prune final-scale tokens beyond 70% (ablation)FastSTAR · T2V scale 29qualityHurt
token pruning instead of token merging (40% ratio) (ablation)FastSTAR · STAR feature mapsMSEImproved
use FastSTAR at 480p vs 720pFastSTAR · T2V/I2V/V2V 480pspeedupMixed

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