i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data

Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang


Abstract
The convergence of text, visual, and audio data is crucial towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models that lack generative abilities. We propose closing this gap with i-Code V2, one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data. i-Code V2 leverages state-of-the-art single-modality encoders, combining their outputs with a new modality-fusing encoder to project combinations of modalities into a shared representational space. Language tokens are generated from these representations via an autoregressive decoder. i-Code V2 is pretrained end-to-end on a large collection of dual- and single-modality datasets with a novel text completion objective that can be generalized across arbitrary combinations of modalities. i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks, demonstrating the power of generative multimodal pretraining across a diversity of tasks and signals.
Anthology ID:
2024.findings-naacl.105
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1615–1627
Language:
URL:
https://aclanthology.org/2024.findings-naacl.105
DOI:
10.18653/v1/2024.findings-naacl.105
Bibkey:
Cite (ACL):
Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, and Xuedong Huang. 2024. i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1615–1627, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (Yang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.105.pdf