# ARM：统一离散表示的自回归大型多模态模型

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-09 08:00
- AIHOT 分数：63
- AIHOT 链接：https://aihot.virxact.com/items/cmq7h8hbj033osl5wjgri2l5o
- 原文链接：https://arxiv.org/abs/2606.11188

## AI 摘要

ARM是一种基于离散表示的自回归模型，将图像理解、生成与编辑统一在下一个token预测框架中。首先训练离散语义视觉tokenizer，通过多目标监督实现语义判别、语言对齐与忠实重建；然后在文本与图像token序列上训练7B自回归模型，自然融合视觉语言感知与生成能力；最后用强化学习优化文本到图像生成与指令引导编辑的偏好对齐，使WISE整体得分从0.50提升至0.56，GEdit-Bench-EN的G_O评分从5.75提升至6.68，并观察到跨任务协同效果。

## 正文

This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework. ARM is built on three efforts: first, we train a discrete semantic visual tokenizer that maps images into compact token sequences. Our tokenizer is supervised with multiple objectives that jointly promote semantic discriminability, language alignment and faithful reconstruction, thereby supporting diverse tasks in a shared latent space. With this, we train a 7B autoregressive model over large-scale text and image token sequences, seamlessly developing vision-language perception and generation capabilities. Finally, to further improve preference-aligned behavior for text-to-image generation and instruction-guided editing, ARM applies reinforcement learning (RL) to optimize task-level objectives such as visual quality, instruction adherence, and edit consistency. Surprisingly, the results show that RL not only substantially improves performance on the target tasks (e.g., raising WISE overall from 0.50 to 0.56, GEdit-Bench-EN G_O from 5.75 to 6.68), but also induces cross-task synergy between text-to-image generation and editing. Collectively, these findings highlight autoregressive modeling, when paired with strong representations and preference optimization, as a scalable foundation for multimodal intelligence. Code: https://github.com/wdrink/ARM.