Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

About

Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation computational cost. Traditional video tokenizers apply a uniform token assignment across temporal blocks of different videos, often wasting tokens on simple, static, or repetitive segments while underserving dynamic or complex ones. To address this inefficiency, we introduce $\textbf{EVATok}$, a framework to produce $\textbf{E}$fficient $\textbf{V}$ideo $\textbf{A}$daptive $\textbf{Tok}$enizers. Our framework estimates optimal token assignments for each video to achieve the best quality-cost trade-off, develops lightweight routers for fast prediction of these optimal assignments, and trains adaptive tokenizers that encode videos based on the assignments predicted by routers. We demonstrate that EVATok delivers substantial improvements in efficiency and overall quality for video reconstruction and downstream AR generation. Enhanced by our advanced training recipe that integrates video semantic encoders, EVATok achieves superior reconstruction and state-of-the-art class-to-video generation on UCF-101, with at least 24.4% savings in average token usage compared to the prior state-of-the-art LARP and our fixed-length baseline.

Tianwei Xiong, Jun Hao Liew, Zilong Huang, Zhijie Lin, Jiashi Feng, Xihui Liu• 2026

Related benchmarks

TaskDatasetResultRank
Video ReconstructionUCF-101
rFVD9.7
39
Video Frame PredictionKinetics-600
gFVD4
38
Class-to-video generationUCF-101
gFVD48
15
Frame predictionK600 (test)
gFVD4
3
Showing 4 of 4 rows

Other info

GitHub

Follow for update