Jeveration: System One Models Now Generate
Summary (Overview)
- New generation paradigm: Jeveration introduces a third paradigm for image generation—parallel typed decisions in a single forward pass—contrasting with autoregressive and diffusion approaches that require sequential sampling.
- Shared random state for coherence: The key innovation is conditioning all code positions on a shared random state ξ, enabling parallel predictions to converge on globally coherent images despite the many-to-one prompt-to-image mapping.
- Two-phase training: The method first learns the image distribution via masked prediction, then uses distribution matching (Di[M]O-style) with confidence-guided correction to teach the model to use the random state effectively.
- Unified architecture: A single frozen VLM (Qwen3.5-4B) with shared LoRA adapters handles text-to-image, image-to-image, and dense prediction tasks in one checkpoint.
- Exceptional efficiency: Generates 512×512 images in 78 ms on one H200, achieving 122× speedup over Janus-Pro-7B while maintaining competitive quality (0.74 GenEval).
Introduction and Theoretical Foundation
Background and Motivation
Image generation is dominated by two paradigms:
- Autoregressive models [11, 40, 44]: generate image tokens sequentially
- Diffusion models [8, 25, 48]: iterative denoising
Both require many sequential model evaluations, increasing inference latency. Jeveration introduces a third paradigm built on System One models (e.g., Jev [1]) that return typed decisions (Choices, Scores) in a single parallel query without extended reasoning.
The Core Challenge: Global Consistency
A single prompt admits many valid images, yet parallel predictions must converge on a coherent whole. The theoretical foundation rests on a key information-theoretic insight:
For independent parallel predictions, the best forward-KL approximation to the true target distribution satisfies:
where denotes entropy. The gap is the target's total correlation—the measure of how strongly codes depend on each other. A coherent image requires this dependence, but independent sampling matches only the marginals , producing incompatible image regions.
Solution: Shared Random State
Jeveration conditions every code position on a shared random state sequence ξ:
Although codes are sampled independently given , their shared dependence on ξ allows the image distribution to capture inter-position dependencies.
Methodology
Architecture
The system builds on a frozen Qwen3.5-4B VLM with:
- Shared LoRA adapters (rank-256) across all tasks
- Task-specific output heads
- TA-TiTok image tokenizer with N = 128 codes per image
Decision tokens are appended to the input:
- Image generation: Initialized from sampled random state ξ (masking with probability ρ = 0.6, uniform random codes for unmasked positions, Gaussian noise σ = 0.1)
- Dense prediction: Serve as spatial queries aligned with visual tokens
Image Code Prediction
Each decision token's final hidden state feeds two complementary branches:
- Codebook branch : projects to code space with classifier initialized from tokenizer's codebook
- Wide branch : zero-initialized direct mapping to code logits
Two-Phase Training
Phase 1: Learning the image distribution (masked prediction)
The visible codes supply image-specific context, enabling the model to learn inter-position dependencies.
Phase 2: Learning image decisions (distribution matching)
where:
- = frozen first-phase model (represents image distribution)
- = auxiliary model tracking θ's current distribution
- = logits from the decision model
- sg = stop-gradient
Confidence-guided correction: Re-mask the half of positions with lowest confidence , complete via frozen model, then train θ to predict corrected codes:
Empirical Validation / Results
Text-to-Image Generation
Key results (Table 1):
| Model | Unified | Params (B) | Steps | Res. (px) | Speedup↑ | GenEval↑ | Latency (ms)↓ |
|---|---|---|---|---|---|---|---|
| Janus-Pro-7B | √ | 7.0 | 576 | 384 | 1.0× | 0.80 | 9,508.4 |
| Show-o Turbo-512 | √ | 1.3 | 4 | 512 | 101.0× | 0.63 | 94.1 |
| Jeveration | √ | 5.2 | 1 | 512 | 122.2× | 0.74 | 77.8 |
- 122× faster than Janus-Pro-7B
- 0.11 GenEval improvement over Show-o Turbo-512 at same resolution
- Higher GenEval than SANA-Sprint 0.6B, FLUX.1-schnell, and SDXL-DMD2 (one-step 1024-px models)
Image-to-Image Generation (Table 2)
| Model | HED | Depth | Colorize | Style PSNR↑ |
|---|---|---|---|---|
| Jeveration | 0.880 | 0.802 | 0.937 | 15.40 |
| Copy the input | 0.828 | 0.713 | 0.998 | - |
| Decoder without source | 0.792 | 0.767 | 0.757 | 14.37 |
Strong structural fidelity across edge maps, depth maps, colorization, and style transfer (anime, Studio Ghibli, watercolor).
Dense Prediction on NYUv2 (Table 3)
| Model | Seg. mIoU↑ | Depth abs.↓ | Depth δ₁↑ | Normal mean (°)↓ |
|---|---|---|---|---|
| Jeveration | 67.7 | 0.267 | 0.898 | 24.2 |
| Dense-only (one task) | 67.8 | 0.246 | 0.915 | 21.2 |
| DeepLabV3+ R50 | 53.5 | 0.393 | - | 22.0 |
Jeveration outperforms DeepLabV3+ by 14.2 mIoU and reduces depth error by 32%.
Ablation Studies (Table 4)
| Variant | GenEval↑ | HPS↑ |
|---|---|---|
| w/ random state | 0.73 | 28.27 |
| w/ fixed state | 0.70 | 26.63 |
| w/ correction target | 0.74 | 28.03 |
| w/o correction target | 0.73 | 27.92 |
| Image head (wide + codebook) | 0.64 | 25.42 |
| Image head (wide only) | 0.60 | 25.34 |
| Image head (codebook only) | 0.59 | 25.04 |
Key findings:
- Random state improves coherence: +0.03 GenEval, +1.64 HPS over fixed state
- Correction target refines details (HPS +0.11)
- Combined head branches outperform either alone (complementary benefits)
Joint Training (Table 5)
Training on all tasks costs almost no text-to-image quality (GenEval 0.74 vs 0.73; HPS 28.06 vs 28.28), demonstrating minimal task interference.
Theoretical and Practical Implications
Theoretical Contributions
- Extends System One paradigm: Demonstrates that decision models can generate, not just decide—broadening the theoretical scope of parallel typed decision frameworks.
- Information-theoretic framing: Formally characterizes why independent parallel prediction fails (total correlation gap) and how shared randomness bridges this gap.
- Distribution matching for parallel generation: Shows that masked models can serve as training targets for single-pass generators within a frozen backbone, avoiding the need to train generative models from scratch.
Practical Implications
- Dramatic latency reduction: 78 ms per image enables real-time and edge deployment scenarios previously infeasible with autoregressive or diffusion approaches.
- Unified visual intelligence: One checkpoint serving generation, editing, and perception tasks simplifies deployment and reduces memory footprints.
- Frozen backbone reuse: Leveraging pretrained VLMs with lightweight adapters makes the approach accessible—training takes only ~4 days on 4× RTX PRO 6000 GPUs.
- Controllable generation at near-zero cost: Image-to-image tasks add only ~14 ms over text-to-image, making conditional generation practical for interactive applications.
Conclusion
Jeveration establishes a third paradigm for image generation where System One models return complete images as single joint decisions. The key innovations—shared random state conditioning and two-phase distribution-matching training—enable globally coherent images from parallel predictions.
Main takeaways:
- A frozen VLM can generate high-quality images (0.74 GenEval) in a single forward pass (78 ms)
- One checkpoint unifies text-to-image, image-to-image, and dense prediction with minimal task interference
- The paradigm extends naturally to diverse visual tasks
Future directions:
- Extension to further visual tasks and modalities (video, 3D, audio)
- Scaling to higher resolutions and larger backbones
- Exploring additional applications of the shared random state mechanism
- Potential integration with other System One decision interfaces (e.g., Box, Scores) for richer multimodal interaction
Related papers
- Wave Forcing: Towards Speed-of-Light Streaming Video Generation
Wave Forcing achieves 134.8 end-to-end FPS on 8 H200s by denoising video chunks in a causal wavefront pattern, matching quality while boosting long-video motion dynamics from 36.63 to 91.45.
- PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations
PDRVLA achieves state-of-the-art robot manipulation success rates by extracting compact physical tokens from intermediate VLM features, supervised via future prediction without costly online video generation.
- SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
SwarmEvolve uses hundreds of low-cost LLM agents reasoning in latent space and communicating via KV caches to achieve 5–13x higher throughput and top scores, matching frontier-model results with an 8B model.