AI Paper Atlas

Research map / Video / Video generation

AdapTok: Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space

Yan Li, Changyao Tian, Renqiu Xia, Ning Liao, Weiwei Guo, Hongsheng Li, Jifeng Dai, Hao Li, Xue Yang

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion

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 AdapTok adaptive tokenizer instead of non-adaptive CausalTokAdapTok · UCF-101 reconstructionrFVD: 37 -> 36 (1,024 tokens); 60 with 512 tokensImproved
use AdapTok tokens instead of CausalTok tokens for autoregressive generationAR generator · UCF-101 class-conditional generationgFVD: 80 -> 67Improved
combine block-mask sampler training with adaptive scorer inference (ablation)AdapTok · UCF-101 reconstructionrFVD: best rFVD 36.36Improved
use ILP allocation instead of fixed, BiThr or BiDelta allocation (ablation)AdapTok · UCF-101 reconstructionFVD, PSNR, LPIPSImproved
use perceptual loss as the scoring metric instead of SSIM, PSNR or MSE (ablation)adaptive scorer · UCF-101 reconstructionrFVDMixed
scale model from AdapTok-S to AdapTok-L (ablation)AdapTok · UCF-101 reconstructionrFVD: 87.32 -> 36.36Improved
scale model from AdapTok-L to AdapTok-XL (ablation)AdapTok · UCF-101 reconstructionrFVD: 36.36 -> 32.43Improved
use scorer with IPAL instead of ElasticTok threshold allocationAdapTok · inference latencylatency: 11x fasterImproved
increase ILP mini-batch size from 8 to 1024 (ablation)IPAL · UCF-101 reconstruction, avg 1024 tokensFVD: 36.55 -> 37.01No 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