AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911141766103040 |
|---|---|
| author | Zhan, Jun Dai, Junqi Ye, Jiasheng Zhou, Yunhua Zhang, Dong Liu, Zhigeng Zhang, Xin Yuan, Ruibin Zhang, Ge Li, Linyang Yan, Hang Fu, Jie Gui, Tao Sun, Tianxiang Jiang, Yu-Gang Qiu, Xipeng |
| author_facet | Zhan, Jun Dai, Junqi Ye, Jiasheng Zhou, Yunhua Zhang, Dong Liu, Zhigeng Zhang, Xin Yuan, Ruibin Zhang, Ge Li, Linyang Yan, Hang Fu, Jie Gui, Tao Sun, Tianxiang Jiang, Yu-Gang Qiu, Xipeng |
| contents | We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. AnyGPT can be trained stably without any alterations to the current large language model (LLM) architecture or training paradigms. Instead, it relies exclusively on data-level preprocessing, facilitating the seamless integration of new modalities into LLMs, akin to the incorporation of new languages. We build a multimodal text-centric dataset for multimodal alignment pre-training. Utilizing generative models, we synthesize the first large-scale any-to-any multimodal instruction dataset. It consists of 108k samples of multi-turn conversations that intricately interweave various modalities, thus equipping the model to handle arbitrary combinations of multimodal inputs and outputs. Experimental results demonstrate that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities, proving that discrete representations can effectively and conveniently unify multiple modalities within a language model. Demos are shown in https://junzhan2000.github.io/AnyGPT.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12226 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling Zhan, Jun Dai, Junqi Ye, Jiasheng Zhou, Yunhua Zhang, Dong Liu, Zhigeng Zhang, Xin Yuan, Ruibin Zhang, Ge Li, Linyang Yan, Hang Fu, Jie Gui, Tao Sun, Tianxiang Jiang, Yu-Gang Qiu, Xipeng Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. AnyGPT can be trained stably without any alterations to the current large language model (LLM) architecture or training paradigms. Instead, it relies exclusively on data-level preprocessing, facilitating the seamless integration of new modalities into LLMs, akin to the incorporation of new languages. We build a multimodal text-centric dataset for multimodal alignment pre-training. Utilizing generative models, we synthesize the first large-scale any-to-any multimodal instruction dataset. It consists of 108k samples of multi-turn conversations that intricately interweave various modalities, thus equipping the model to handle arbitrary combinations of multimodal inputs and outputs. Experimental results demonstrate that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities, proving that discrete representations can effectively and conveniently unify multiple modalities within a language model. Demos are shown in https://junzhan2000.github.io/AnyGPT.github.io/ |
| title | AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.12226 |