Takuya Yoshioka


2024

pdf bib
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
Findings of the Association for Computational Linguistics: NAACL 2024

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.