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/
@article{arxiv.2402.12226,
title = {AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling},
author = {Jun Zhan and Junqi Dai and Jiasheng Ye and Yunhua Zhou and Dong Zhang and Zhigeng Liu and Xin Zhang and Ruibin Yuan and Ge Zhang and Linyang Li and Hang Yan and Jie Fu and Tao Gui and Tianxiang Sun and Yu-Gang Jiang and Xipeng Qiu},
journal= {arXiv preprint arXiv:2402.12226},
year = {2025}
}
Comments
28 pages, 16 figures, under review, work in progress