In this paper, we introduce MIO, a novel foundation model built on multimodal tokens, capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner. While the emergence of large language models (LLMs) and multimodal large language models (MM-LLMs) propels advancements in artificial general intelligence through their versatile capabilities, they still lack true any-to-any understanding and generation. Recently, the release of GPT-4o has showcased the remarkable potential of any-to-any LLMs for complex real-world tasks, enabling omnidirectional input and output across images, speech, and text. However, it is closed-source and does not support the generation of multimodal interleaved sequences. To address this gap, we present MIO, which is trained on a mixture of discrete tokens across four modalities using causal multimodal modeling. MIO undergoes a four-stage training process: (1) alignment pre-training, (2) interleaved pre-training, (3) speech-enhanced pre-training, and (4) comprehensive supervised fine-tuning on diverse textual, visual, and speech tasks. Our experimental results indicate that MIO exhibits competitive, and in some cases superior, performance compared to previous dual-modal baselines, any-to-any model baselines, and even modality-specific baselines. Moreover, MIO demonstrates advanced capabilities inherent to its any-to-any feature, such as interleaved video-text generation, chain-of-visual-thought reasoning, visual guideline generation, instructional image editing, etc.

翻译：本文介绍了MIO，一种基于多模态令牌构建的新型基础模型，能够以端到端、自回归的方式理解和生成语音、文本、图像及视频。尽管大型语言模型（LLMs）和多模态大型语言模型（MM-LLMs）凭借其多功能性推动了通用人工智能的进步，但它们仍缺乏真正的任意模态间理解与生成能力。近期发布的GPT-4o展示了任意模态LLMs在复杂现实任务中的巨大潜力，实现了跨图像、语音和文本的全方位输入输出。然而，该系统是闭源的，且不支持生成多模态交错序列。为填补这一空白，我们提出了MIO，该模型通过因果多模态建模，在四种模态的离散令牌混合数据上进行训练。MIO经历了四阶段训练流程：（1）对齐预训练，（2）交错预训练，（3）语音增强预训练，以及（4）针对多样化文本、视觉和语音任务的综合监督微调。实验结果表明，与先前的双模态基线、任意模态模型基线乃至特定模态基线相比，MIO展现出具有竞争力、甚至在某些情况下更优的性能。此外，MIO还表现出其任意模态特性所固有的先进能力，例如交错视频-文本生成、视觉思维链推理、视觉指南生成、指令性图像编辑等。