paper-with-me

홈 › Papers

MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control

2024-03-18 · Enshen Zhou, Yiran Qin, Zhenfei Yin, Yuzhou Huang, Ruimao Zhang, Lu Sheng, Yu Qiao, Jing Shao

It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways. However, existing approaches often fail to steadily follow instructions due to difficulties in understanding abstract and sequential natural language instructions. To this end, we introduce MineDreamer, an open-ended embodied agent built upon the challenging Minecraft simulator with an innovative paradigm that enhances instruction-following ability in low-level control signal generation. Specifically, MineDreamer is developed on top of recent advances in Multimodal Large Language Models (MLLMs) and diffusion models, and we employ a Chain-of-Imagination (CoI) mechanism to envision the step-by-step process of executing instructions and translating imaginations into more precise visual prompts tailored to the current state; subsequently, the agent generates keyboard-and-mouse actions to efficiently achieve these imaginations, steadily following the instructions at each step. Extensive experiments demonstrate that MineDreamer follows single and multi-step instructions steadily, significantly outperforming the best generalist agent baseline and nearly doubling its performance. Moreover, qualitative analysis of the agent's imaginative ability reveals its generalization and comprehension of the open world.

📄 PDF Abstract BibTeX arXiv:2403.12037

Code (1)

Zhoues/MineDreamer 공식 구현 pytorch

Tasks

Instruction FollowingMinecraft

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Creative Agents: Empowering Agents with Imagination for Creative Tasks

2023-12-05 · Chi Zhang, Penglin Cai, Yuhui Fu, Haoqi Yuan 외

We study building embodied agents for open-ended creative tasks. While existing methods build instruction-following agents that can perform diverse open-ended tasks, none of them demonstrates creativity -- the ability to…

Instruction FollowingLanguage ModellingLarge Language ModelMinecraft

VISTAv2: World Imagination for Indoor Vision-and-Language Navigation

2025-11-14 · Yanjia Huang, Xianshun Jiang, Xiangbo Gao, Mingyang Wu 외 arxiv

Vision-and-Language Navigation (VLN) requires agents to follow language instructions while acting in continuous real-world spaces. Prior image imagination based VLN work shows benefits for discrete panoramas but lacks on…

Do Visual Imaginations Improve Vision-and-Language Navigation Agents?

2025-03-20 · CVPR 2025 1 · Akhil Perincherry, Jacob Krantz, Stefan Lee

Vision-and-Language Navigation (VLN) agents are tasked with navigating an unseen environment using natural language instructions. In this work, we study if visual representations of sub-goals implied by the instructions …

Vision and Language Navigation

Stimulating Imagination: Towards General-purpose Object Rearrangement

2024-08-03 · Jianyang Wu, Jie Gu, Xiaokang Ma, Chu Tang 외

General-purpose object placement is a fundamental capability of an intelligent generalist robot, i.e., being capable of rearranging objects following human instructions even in novel environments. To achieve this, we bre…

ObjectObject LocalizationObject RearrangementPose Estimation

Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models

2024-02-18 · Shirley Anugrah Hayati, Taehee Jung, Tristan Bodding-Long, Sudipta Kar 외

Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. However, most existing instruction datasets …