Image de couverture de livre

Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gu, Songen, Cai, Yunuo, Wang, Tianyu, Wu, Simo, Fu, Yanwei
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation
par: Zhou, Pengfei, et autres
Publié: (2026)

VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation
par: Yu, Xinglei, et autres
Publié: (2026)

ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
par: Liu, Zhenyang, et autres
Publié: (2026)

OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation
par: Zheng, Yuhang, et autres
Publié: (2026)

Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models
par: Wang, Tianyu, et autres
Publié: (2024)

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
par: Barcellona, Leonardo, et autres
Publié: (2024)

DreamGen: Unlocking Generalization in Robot Learning through Video World Models
par: Jang, Joel, et autres
Publié: (2025)

GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation
par: Zhang, Zijian, et autres
Publié: (2026)

TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
par: Xu, Qinwen, et autres
Publié: (2026)

VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
par: Gu, Songen, et autres
Publié: (2026)

Optimizing Robotic Manipulation with Decision-RWKV: A Recurrent Sequence Modeling Approach for Lifelong Learning
par: Dong, Yujian, et autres
Publié: (2024)

Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?
par: Zhang, Zhongru, et autres
Publié: (2026)

TriVLA: A Triple-System-Based Unified Vision-Language-Action Model with Episodic World Modeling for General Robot Control
par: Liu, Zhenyang, et autres
Publié: (2025)

World Models for Robotic Manipulation: A Survey
par: Wang, Fangyuan, et autres
Publié: (2026)

Learning Robot Manipulation from Audio World Models
par: Zhang, Fan, et autres
Publié: (2025)

OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation
par: Wang, Kuanning, et autres
Publié: (2026)

Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation
par: Song, Zijian, et autres
Publié: (2026)

AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulation
par: Yuan, Ge, et autres
Publié: (2026)

Learning Versatile Humanoid Manipulation with Touch Dreaming
par: Niu, Yaru, et autres
Publié: (2026)

Instruct2Act: From Human Instruction to Actions Sequencing and Execution via Robot Action Network for Robotic Manipulation
par: Sharma, Archit, et autres
Publié: (2026)

STORM: Search-Guided Generative World Models for Robotic Manipulation
par: Lin, Wenjun, et autres
Publié: (2025)

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
par: Fang, Haoquan, et autres
Publié: (2025)

Imagine2Act: Leveraging Object-Action Motion Consistency from Imagined Goals for Robotic Manipulation
par: Heng, Liang, et autres
Publié: (2025)

EEG-Driven AR-Robot System for Zero-Touch Grasping Manipulation
par: Wang, Junzhe, et autres
Publié: (2025)

World In Your Hands: A Large-Scale and Open-Source Ecosystem for Learning Human-Centric Manipulation in the Wild
par: Zheng, Yupeng, et autres
Publié: (2025)

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
par: Dharmarajan, Karthik, et autres
Publié: (2025)

Learning Instruction-Guided Manipulation Affordance via Large Models for Embodied Robotic Tasks
par: Li, Dayou, et autres
Publié: (2024)

Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation
par: Wang, Guokang, et autres
Publié: (2024)

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
par: Zhang, Chuanrui, et autres
Publié: (2025)

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation
par: Yao, Yuanqi, et autres
Publié: (2025)

RoboDream: Compositional World Models for Scalable Robot Data Synthesis
par: Ye, Junjie, et autres
Publié: (2026)

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
par: Gao, Shenyuan, et autres
Publié: (2026)

VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
par: Zhao, Wei, et autres
Publié: (2025)

GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
par: Zhou, Kaichen, et autres
Publié: (2026)

DreamPlan: Efficient Reinforcement Fine-Tuning of Vision-Language Planners via Video World Models
par: Jia, Emily Yue-Ting, et autres
Publié: (2026)

STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation
par: Tian, Yuxuan, et autres
Publié: (2026)

DreamToNav: Generalizable Navigation for Robots via Generative Video Planning
par: Serpiva, Valerii, et autres
Publié: (2026)

Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
par: Bai, Yongjie, et autres
Publié: (2025)

RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation
par: Li, Huiqiong, et autres
Publié: (2026)

iManip: Skill-Incremental Learning for Robotic Manipulation
par: Zheng, Zexin, et autres
Publié: (2025)