| title | Jeveration: System One Models Now Generate |
|---|---|
| authors | Yuhe Liu, Qi Li, Shihua Zhang, Xinchao Wang |
| date | 2026-11-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.24738 |
| affiliation | National University of Singapore |
| upvotes | 146 (Hugging Face Daily Papers, 2026-11-21) |
| links | abs pdf hf code |
| cite | |
| related | Jeva: System One Models from First Principles SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation AI for Games in the Foundation Model Era MaLiang-Harness: A Programmable Path to Image and Video Generation |
| abstract | System One models such as Jev return decisions through fast, parallel prediction. In this paper, we introduce Jeveration, showing that the same decision paradigm can also generate high-quality images in a single forward pass. Jeveration builds on a frozen vision-language model, repurposing its visual-semantic knowledge for holistic image generation. The key challenge is to maintain global consistency. A single prompt admits many valid images, yet parallel predictions must converge on a coherent whole. We therefore condition all positions on a shared random state to coordinate parallel predictions, so that each draw yields a different but coherent image. Since the model tends to ignore this state under direct image supervision, we first learn a distribution over discrete image codes to guide single-pass generation. Beyond text-to-image generation, we further unify image-to-image generation and dense prediction within the same architecture, so that one checkpoint supports all three tasks, each in one forward pass. Experiments show that Jeveration generates a 512x512 image in 78 ms, up to 122x faster than existing unified models, while maintaining competitive image quality and dense prediction performance. |
bibtex
@misc{liu2026jeveration,
title={Jeveration: System One Models Now Generate},
author={Yuhe Liu and Qi Li and Shihua Zhang and Xinchao Wang},
year={2026},
eprint={2611.24738},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.24738}
}