用自回归归一化流统一图文生成，让模型像写文字一样生成图像。
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
- 用与大语言模型同构的自回归归一化流，实现图文无缝交替生成。
- 支持缓存复用，图文输出直接进缓存，生成效率更高。
- 适合需要高效多模态生成的场景，如对话式图像创作。
深度生成模型在文本和视觉领域快速发展，推动了能理解、推理并生成交错图文序列的统一多模态系统的发展。现有方法多将自回归语言建模与基于扩散的图像生成结合，但其因果文本生成与迭代去噪视觉生成存在结构不匹配。我们观察到自回归归一化流本质上是自回归Transformer——共享相同的因果掩码、键值缓存机制和从左到右的结构，因此是最自然的统一多模态生成范式。我们提出STARFlow2，基于Pretzel架构，通过残差跳连垂直交织预训练视觉语言模型（VLM）流与TarFlow流，两者共享同一因果掩码。结合深浅层流设计与统一的FAE潜在空间，STARFlow2实现了缓存友好的交错生成，文本和视觉输出可直接进入键值缓存，无需重新编码。实验表明，该模型在图像生成与多模态理解基准上表现优异，验证了自回归流作为统一多模态建模基础的可行性。
原文摘要 · Abstract (English)
Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine autoregressive language modeling with diffusion-based image generators, inheriting a structural mismatch between causal text generation and iterative visual denoising. We observe that autoregressive normalizing flows are autoregressive Transformers--sharing the same causal mask, KV-cache mechanism, and left-to-right structure as LLMs--making them the most natural paradigm for true unified multimodal generation. We present STARFlow2, built on the Pretzel architecture that vertically interleaves a pretrained VLM stream with a TarFlow stream via residual skip connections, both operating under the same causal mask. Combined with a deep-shallow flow design and a unified FAE latent space, STARFlow2 enables cache-friendly interleaved generation where both text and visual outputs directly enter the KV-cache without re-encoding. Experiments demonstrate strong performance across image generation and multimodal understanding benchmarks, validating autoregressive flows as a viable foundation for unified multimodal modeling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。