PandaGPT: One Model To Instruction-Follow Them All

Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, Deng Cai


Abstract
We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. More interestingly, PandaGPT can take multimodal inputs simultaneously and compose their semantics naturally. For example, PandaGPT can connect how objects look in an image/video and how they sound in an audio. To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna. Notably, only aligned image-text pairs are required for the training of PandaGPT. Thanks to the strong capability of ImageBind in embedding data from different modalities into the same space, PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU). We hope that PandaGPT serves as an initial step toward building AGI that can perceive and understand inputs in different modalities holistically, as we humans do.
Anthology ID:
2023.tllm-1.2
Volume:
Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants!
Month:
September
Year:
2023
Address:
Prague, Czech Republic
Editors:
Devamanyu Hazarika, Xiangru Robert Tang, Di Jin
Venues:
TLLM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11–23
Language:
URL:
https://aclanthology.org/2023.tllm-1.2
DOI:
Bibkey:
Cite (ACL):
Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, and Deng Cai. 2023. PandaGPT: One Model To Instruction-Follow Them All. In Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants!, pages 11–23, Prague, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
PandaGPT: One Model To Instruction-Follow Them All (Su et al., TLLM-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.tllm-1.2.pdf