paper-with-me

홈 › Papers

WorldGPT: Empowering LLM as Multimodal World Model

2024-04-28 · Zhiqi Ge, Hongzhe Huang, Mingze Zhou, Juncheng Li, Guoming Wang, Siliang Tang, Yueting Zhuang

World models are progressively being employed across diverse fields, extending from basic environment simulation to complex scenario construction. However, existing models are mainly trained on domain-specific states and actions, and confined to single-modality state representations. In this paper, We introduce WorldGPT, a generalist world model built upon Multimodal Large Language Model (MLLM). WorldGPT acquires an understanding of world dynamics through analyzing millions of videos across various domains. To further enhance WorldGPT's capability in specialized scenarios and long-term tasks, we have integrated it with a novel cognitive architecture that combines memory offloading, knowledge retrieval, and context reflection. As for evaluation, we build WorldNet, a multimodal state transition prediction benchmark encompassing varied real-life scenarios. Conducting evaluations on WorldNet directly demonstrates WorldGPT's capability to accurately model state transition patterns, affirming its effectiveness in understanding and predicting the dynamics of complex scenarios. We further explore WorldGPT's emerging potential in serving as a world simulator, helping multimodal agents generalize to unfamiliar domains through efficiently synthesising multimodal instruction instances which are proved to be as reliable as authentic data for fine-tuning purposes. The project is available on \url{https://github.com/DCDmllm/WorldGPT}.

📄 PDF Abstract BibTeX arXiv:2404.18202

Code (1)

dcdmllm/worldgpt 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language ModelmodelMultimodal Large Language Model

Similar Papers 제목 키워드 기반

WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs

2024-03-10 · Deshun Yang, Luhui Hu, Yu Tian, Zihao Li 외

Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and …

AI AgentVideo Generation

Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs

2023-11-27 · Yunxin Li, Baotian Hu, Wei Wang, Xiaochun Cao 외

Recent advancements in multimodal large language models (MLLMs) have achieved significant multimodal generation capabilities, akin to GPT-4. These models predominantly map visual information into language representation …

Instruction Followingmultimodal generationText Generation

Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator

2023-12-11 · Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou

Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but few research studies aim to gauge the ability to generate visual instruction tuning data. This paper proposes to explore …

Image CaptioningQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Position: Empowering Time Series Reasoning with Multimodal LLMs

2025-02-03 · Yaxuan Kong, Yiyuan Yang, Shiyu Wang, Chenghao Liu 외

Understanding time series data is crucial for multiple real-world applications. While large language models (LLMs) show promise in time series tasks, current approaches often rely on numerical data alone, overlooking the…

Decision MakingMultimodal ReasoningPositionTime Series+1

CaMML: Context-Aware Multimodal Learner for Large Models

2024-01-06 · Yixin Chen, Shuai Zhang, Boran Han, Tong He 외

In this work, we introduce Context-Aware MultiModal Learner (CaMML), for tuning large multimodal models (LMMs). CaMML, a lightweight module, is crafted to seamlessly integrate multimodal contextual samples into large mod…

Visual Question Answering