Explore the Limits of Omni-modal Pretraining at Scale
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913390641807360 |
|---|---|
| author | Zhang, Yiyuan Li, Handong Liu, Jing Yue, Xiangyu |
| author_facet | Zhang, Yiyuan Li, Handong Liu, Jing Yue, Xiangyu |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09412 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explore the Limits of Omni-modal Pretraining at Scale Zhang, Yiyuan Li, Handong Liu, Jing Yue, Xiangyu Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia 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 |
| title | Explore the Limits of Omni-modal Pretraining at Scale |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia |
| url | https://arxiv.org/abs/2406.09412 |