AI Paper Atlas

Research map / Video / Video generation

TokensGen: Harnessing Condensed Tokens for Long Video Generation

Wenqi Ouyang, Zeqi Xiao, Danni Yang, Yifan Zhou, Shuai Yang, Lei Yang, Jianlou Si, Xingang Pan

ICCV 2025 · Video › Video generation · approach: Compositional text-to-video diffusion · 4 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
use condensed tokens 4x8x12 instead of 4x5x7 (ablation)TokensGen To2V · To2V reconstructionMSE: 2.84e-2 -> 1.24e-2Improved
increase token spatial size from 5x7 to 8x12 at 4 frames vs 13x5x7 (ablation)TokensGen To2V · To2V reconstructionMSE: 1.54e-2 -> 1.24e-2Improved
add PCA channel projection to condensed tokens (ablation)TokensGen To2V · To2V reconstructionMSE / SSIM: 1.24e-2 -> 1.24e-2; SSIM 0.62 -> 0.62No clear effect
use condensed tokens instead of super-resolution conditioning (ablation)TokensGen To2V · To2V reconstructionSSIM: 0.60 -> 0.62; MSE 1.12e-2 -> 1.24e-2Mixed
use condensed tokens instead of super-resolution conditioning (ablation)TokensGen To2V · To2V reconstructiontemporal flickering: 97.10 -> 97.58Improved
add FIFO-Diffusion to clip-wise generation (ablation)TokensGen · long videovisual consistencyImproved
add adaptive padding to FIFO (ablation)TokensGen · long videoinitial-frame qualityImproved
use TokensGen instead of AP-FIFO+CogVideoXlong video generation · Human studyText-Visual Alignment: 24.31% -> 75.69%Improved
use TokensGen instead of AP-FIFO+CogVideoXlong video generation · Human studyMotion & Content Consistency: 22.57% -> 75.74%Improved
use TokensGen instead of AP-FIFO+CogVideoXlong video generation · VBenchSubject Consistency: 86.22 -> 84.57Hurt
use TokensGen instead of AP-FIFO+CogVideoXlong video generation · VBenchMotion Smoothness: 97.48 -> 98.08Improved
use TokensGen instead of AP-FIFO+CogVideoXlong video generation · VBenchDynamic Degree: 78.57 -> 78.95No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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