titleJeveration: System One Models Now Generate
authorsYuhe Liu, Qi Li, Shihua Zhang, Xinchao Wang
date2026-11-18
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.24738
affiliationNational University of Singapore
upvotes146 (Hugging Face Daily Papers, 2026-11-21)
linksabs pdf hf code
cite
relatedJeva: 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
abstractSystem 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}
}