# Visual Self-Refinement for Autoregressive Models

arXiv: https://arxiv.org/abs/2510.00993 · HTML: https://mlsanity.com/paper/2510.00993/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [NewsQA: A Machine Comprehension Dataset](https://mlsanity.com/paper/1611.09830/) (2016)
- [Sequential Modeling Enables Scalable Learning for Large Vision Models](https://mlsanity.com/paper/2312.00785/) (2023)
- [Scalable Pre-training of Large Autoregressive Image Models](https://mlsanity.com/paper/2401.08541/) (2024)
- [STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering](https://mlsanity.com/paper/2406.19973/) (2024)
- [SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant](https://mlsanity.com/paper/2403.11299/) (2024)
- [Elucidating the design space of language models for image generation](https://mlsanity.com/paper/2410.16257/) (2024)
- [Modeling Mask Uncertainty in Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2112.15362/) (2021)
- [Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging](https://mlsanity.com/paper/2306.01176/) (2023)

## Built on by (most cited first, 2 of 2)

- [Knowledge Distillation for Visual Autoregressive Models](https://mlsanity.com/paper/2606.06078/) (2026)
- [Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling](https://mlsanity.com/paper/2609.11804/) (2026)

## Abstract (arXiv)

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to suboptimal results. This work proposes a plug-and-play refinement module to enhance the complex spatial correspondence modeling within the generated visual sequence. This module operates as a post-pretraining step to jointly refine all generated tokens of autoregressive model, enhancing vision-language modeling under a shared sequential prediction framework. By leveraging global context and relationship across the tokens, our method mitigates the error accumulation issue within the sequential generation. Experiments demonstrate that the proposed method improves the generation quality, enhancing the model's ability to produce semantically consistent results.