# Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

arXiv: https://arxiv.org/abs/2602.07022 · HTML: https://mlsanity.com/paper/2602.07022/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 29 of 29)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer](https://mlsanity.com/paper/2303.14389/) (2023)
- [More Control for Free! Image Synthesis with Semantic Diffusion Guidance](https://mlsanity.com/paper/2112.05744/) (2021)
- [Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining](https://mlsanity.com/paper/2408.02657/) (2024)
- [Randomized Autoregressive Visual Generation](https://mlsanity.com/paper/2411.00776/) (2024)
- [DiffiT: Diffusion Vision Transformers for Image Generation](https://mlsanity.com/paper/2312.02139/) (2023)
- [ImageFolder: Autoregressive Image Generation with Folded Tokens](https://mlsanity.com/paper/2410.01756/) (2024)
- [GIVT: Generative Infinite-Vocabulary Transformers](https://mlsanity.com/paper/2312.02116/) (2023)
- [Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models](https://mlsanity.com/paper/2405.14861/) (2024)
- [Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance](https://mlsanity.com/paper/2212.06359/) (2022)
- [Multimodal Latent Language Modeling with Next-Token Diffusion](https://mlsanity.com/paper/2412.08635/) (2024)
- [Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation](https://mlsanity.com/paper/2505.24787/) (2025)
- [MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling](https://mlsanity.com/paper/2410.10798/) (2024)
- [Speed Always Wins: A Survey on Efficient Architectures for Large Language Models](https://mlsanity.com/paper/2508.09834/) (2025)
- [Seismic Data Interpolation via Denoising Diffusion Implicit Models with Coherence-corrected Resampling](https://mlsanity.com/paper/2307.04226/) (2023)

## Built on by (most cited first, 9 of 9)

- [Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees](https://mlsanity.com/paper/2603.22355/) (2026)
- [Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity](https://mlsanity.com/paper/2604.07402/) (2026)
- [Multimodal Large Language Models for Multi-Subject In-Context Image Generation](https://mlsanity.com/paper/2604.07422/) (2026)
- [LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models](https://mlsanity.com/paper/2603.13450/) (2026)
- [AE-LLM: Adaptive Efficiency Optimization for Large Language Models](https://mlsanity.com/paper/2603.20492/) (2026)
- [UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image Generators](https://mlsanity.com/paper/2604.11843/) (2026)
- [MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models](https://mlsanity.com/paper/2605.28825/) (2026)
- [HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type Classification](https://mlsanity.com/paper/2606.26100/) (2026)
- [Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation](https://mlsanity.com/paper/2607.09803/) (2026)

## Abstract (arXiv)

Recent studies have explored autoregressive models for image generation, with promising results, and have combined diffusion models with autoregressive frameworks to optimize image generation via diffusion losses. In this study, we present a theoretical analysis of diffusion and autoregressive models with diffusion loss, highlighting the latter's advantages. We present a theoretical comparison of conditional diffusion and autoregressive diffusion with diffusion loss, demonstrating that patch denoising optimization in autoregressive models effectively mitigates condition errors and leads to a stable condition distribution. Our analysis also reveals that autoregressive condition generation refines the condition, causing the condition error influence to decay exponentially. In addition, we introduce a novel condition refinement approach based on Optimal Transport (OT) theory to address ``condition inconsistency''. We theoretically demonstrate that formulating condition refinement as a Wasserstein Gradient Flow ensures convergence toward the ideal condition distribution, effectively mitigating condition inconsistency. Experiments demonstrate the superiority of our method over diffusion and autoregressive models with diffusion loss methods.