DreamLLM: Synergistic Multimodal Comprehension and Creation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dong, Runpei, Han, Chunrui, Peng, Yuang, Qi, Zekun, Ge, Zheng, Yang, Jinrong, Zhao, Liang, Sun, Jianjian, Zhou, Hongyu, Wei, Haoran, Kong, Xiangwen, Zhang, Xiangyu, Ma, Kaisheng, Yi, Li
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929278564696064
author Dong, Runpei
Han, Chunrui
Peng, Yuang
Qi, Zekun
Ge, Zheng
Yang, Jinrong
Zhao, Liang
Sun, Jianjian
Zhou, Hongyu
Wei, Haoran
Kong, Xiangwen
Zhang, Xiangyu
Ma, Kaisheng
Yi, Li
author_facet Dong, Runpei
Han, Chunrui
Peng, Yuang
Qi, Zekun
Ge, Zheng
Yang, Jinrong
Zhao, Liang
Sun, Jianjian
Zhou, Hongyu
Wei, Haoran
Kong, Xiangwen
Zhang, Xiangyu
Ma, Kaisheng
Yi, Li
contents This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation. DreamLLM operates on two fundamental principles. The first focuses on the generative modeling of both language and image posteriors by direct sampling in the raw multimodal space. This approach circumvents the limitations and information loss inherent to external feature extractors like CLIP, and a more thorough multimodal understanding is obtained. Second, DreamLLM fosters the generation of raw, interleaved documents, modeling both text and image contents, along with unstructured layouts. This allows DreamLLM to learn all conditional, marginal, and joint multimodal distributions effectively. As a result, DreamLLM is the first MLLM capable of generating free-form interleaved content. Comprehensive experiments highlight DreamLLM's superior performance as a zero-shot multimodal generalist, reaping from the enhanced learning synergy. Project page: https://dreamllm.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11499
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DreamLLM: Synergistic Multimodal Comprehension and Creation
Dong, Runpei
Han, Chunrui
Peng, Yuang
Qi, Zekun
Ge, Zheng
Yang, Jinrong
Zhao, Liang
Sun, Jianjian
Zhou, Hongyu
Wei, Haoran
Kong, Xiangwen
Zhang, Xiangyu
Ma, Kaisheng
Yi, Li
Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation. DreamLLM operates on two fundamental principles. The first focuses on the generative modeling of both language and image posteriors by direct sampling in the raw multimodal space. This approach circumvents the limitations and information loss inherent to external feature extractors like CLIP, and a more thorough multimodal understanding is obtained. Second, DreamLLM fosters the generation of raw, interleaved documents, modeling both text and image contents, along with unstructured layouts. This allows DreamLLM to learn all conditional, marginal, and joint multimodal distributions effectively. As a result, DreamLLM is the first MLLM capable of generating free-form interleaved content. Comprehensive experiments highlight DreamLLM's superior performance as a zero-shot multimodal generalist, reaping from the enhanced learning synergy. Project page: https://dreamllm.github.io.
title DreamLLM: Synergistic Multimodal Comprehension and Creation
topic Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
url https://arxiv.org/abs/2309.11499