Papers › TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction

TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction

27 May 2024arXiv:2405.16847archive 2025-07-28

Yinda Chen, Haoyuan Shi, Xiaoyu Liu, Te Shi, Ruobing Zhang, Dong Liu, Zhiwei Xiong, Feng Wu

Autoregressive next-token prediction is a standard pretraining method for large-scale language models, but its application to vision tasks is hindered by the non-sequential nature of image data, leading to cumulative errors. Most vision models employ masked autoencoder (MAE) based pretraining, which faces scalability issues. To address these challenges, we introduce \textbf{TokenUnify}, a novel pretraining method that integrates random token prediction, next-token prediction, and next-all token prediction. We provide theoretical evidence demonstrating that TokenUnify mitigates cumulative errors in visual autoregression. Cooperated with TokenUnify, we have assembled a large-scale electron microscopy (EM) image dataset with ultra-high resolution, ideal for creating spatially correlated long sequences. This dataset includes over 120 million annotated voxels, making it the largest neuron segmentation dataset to date and providing a unified benchmark for experimental validation. Leveraging the Mamba network inherently suited for long-sequence modeling on this dataset, TokenUnify not only reduces the computational complexity but also leads to a significant 45\% improvement in segmentation performance on downstream EM neuron segmentation tasks compared to existing methods. Furthermore, TokenUnify demonstrates superior scalability over MAE and traditional autoregressive methods, effectively bridging the gap between pretraining strategies for language and vision models. Code is available at \url{https://github.com/ydchen0806/TokenUnify}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ydchen0806/tokenunify mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

MambaPredictionSegmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MAE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections