Explore the Limits of Omni-modal Pretraining at Scale
This work addresses the problem of developing universal multimodal AI systems, representing a significant advancement rather than an incremental improvement.
The paper tackles the challenge of building omni-modal intelligence by proposing MiCo, a scalable pretraining paradigm that handles multiple modalities, achieving 37 new state-of-the-art records across tasks like perception, cross-modality understanding, and multimodal language modeling.
We propose to build omni-modal intelligence, which is capable of understanding any modality and learning universal representations. In specific, we propose a scalable pretraining paradigm, named Multimodal Context (MiCo), which can scale up the numbers of modalities and amount of data, together with the model parameters, in the pretraining process. With MiCo, the pretrained models show significant emergent abilities in multimodal learning, which are evaluated on the following tasks: i) single-modality perception benchmarks of 10 different modalities, ii) 25 cross-modality understanding tasks of retrieval, question-answering, captioning, and iii) 18 multimodal large language model benchmarks. Our models establish 37 new records for state-of-the-art performance. We hope that our research could contribute to the development of omni-modal intelligence. Code and Models are at https://github.com/invictus717/MiCo