MODUS：仅解码器的多样模态任意到任意建模

摘要

任意到任意模型能够在单一网络中，根据任意其他模态的组合预测任意模态，这种框架广泛应用于多模态视觉与视觉-语言模型，并逐步扩展至生态学、天文学等科学领域。现有任意到任意模型通常采用编码器-解码器或扩散架构从头训练，这限制了其性能，且无法利用强预训练的仅解码器模型作为先验知识。本研究探索了仅解码器的任意到任意多模态建模，该方法对称处理所有模态，支持任意模态作为输入或输出，无需模态特定的头部结构、损失函数或任务流水线。由于所有模态既是同一模型的输入又是输出，所提出的模型命名为Modus，可支持多种应用场景，例如通过中间模态进行链式生成，或利用另一生成模态对模型自身输出进行评分实现跨模态自验证。Modus展现出卓越的即用性能，在多个基准测试中，单一模型即可与专家模型及多任务基线相竞争。所有相关材料已开源发布于 https://modus-multimodal.epfl.ch/。

English

Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly in scientific domains such as ecology and astronomy. Existing any-to-any models are typically trained from scratch using encoder-decoder or diffusion architectures, impacting their performance and preventing them from using strong pre-trained decoder-only models as a prior. In this work, we investigate decoder-only any-to-any multimodal modeling, which treats all modalities symmetrically and supports arbitrary modalities as inputs and outputs without modality-specific heads, losses, or task pipelines. Because every modality is both an input and an output of the same model, the resulting model, named Modus, can support a range of applications, such as chained generation through intermediate modalities or cross-modal self-verification by scoring the model's own outputs with another generated modality. Modus demonstrates strong out-of-the-box performance and is competitive with specialist and multitask baselines using a single model across various benchmarks. All materials are open-sourced at https://modus-multimodal.epfl.ch/.