Cover Image

Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Zijian, Li, Qichang, Qin, Sihan, Chen, Yuhao, Chen, Tianshui, Lin, Liang, Wang, Guangrun
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Robotic Manipulation is Vision-to-Geometry Mapping ($f(v) \rightarrow G$): Vision-Geometry Backbones over Language and Video Models
by: Song, Zijian, et al.
Published: (2026)

Physical Autoregressive Model for Robotic Manipulation without Action Pretraining
by: Song, Zijian, et al.
Published: (2025)

RADAR: Benchmarking Vision-Language-Action Generalization via Real-World Dynamics, Spatial-Physical Intelligence, and Autonomous Evaluation
by: Chen, Yuhao, et al.
Published: (2026)

ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
by: Chen, Yuzhi, et al.
Published: (2026)

Hyperbolic Multiview Pretraining for Robotic Manipulation
by: Yang, Jin, et al.
Published: (2026)

Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
by: Li, Qixiu, et al.
Published: (2025)

$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation
by: Zhou, Pengfei, et al.
Published: (2026)

GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
by: Zhou, Kaichen, et al.
Published: (2026)

ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning
by: Chen, Yiting, et al.
Published: (2026)

Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation
by: Gu, Songen, et al.
Published: (2026)

VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling
by: Li, Weiqi, et al.
Published: (2025)

World Models for Robotic Manipulation: A Survey
by: Wang, Fangyuan, et al.
Published: (2026)

Stable Language Guidance for Vision-Language-Action Models
by: Zhan, Zhihao, et al.
Published: (2026)

Learning Robot Manipulation from Audio World Models
by: Zhang, Fan, et al.
Published: (2025)

Empowering Multi-Robot Cooperation via Sequential World Models
by: Zhao, Zijie, et al.
Published: (2025)

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
by: Jiang, Zhennan, et al.
Published: (2025)

RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation
by: Li, Huiqiong, et al.
Published: (2026)

GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation
by: Zhang, Zijian, et al.
Published: (2026)

OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation
by: Zheng, Yuhang, et al.
Published: (2026)

Ctrl-World: A Controllable Generative World Model for Robot Manipulation
by: Guo, Yanjiang, et al.
Published: (2025)

H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos
by: Li, Guangrun, et al.
Published: (2025)

Visual Robotic Manipulation with Depth-Aware Pretraining
by: Wang, Wanying, et al.
Published: (2024)

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
by: Zhang, Chuanrui, et al.
Published: (2025)

PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation
by: Li, Wenxuan, et al.
Published: (2025)

RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation
by: Chen, Zixuan, et al.
Published: (2025)

Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interaction
by: Jiang, Shuo, et al.
Published: (2025)

Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
by: Bai, Shuanghao, et al.
Published: (2025)

STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation
by: Tian, Yuxuan, et al.
Published: (2026)

OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
by: Liu, Yushan, et al.
Published: (2026)

A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
by: Wang, Yilin, et al.
Published: (2025)

A General One-Shot Multimodal Active Perception Framework for Robotic Manipulation: Learning to Predict Optimal Viewpoint
by: Qin, Deyun, et al.
Published: (2026)

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
by: Li, Jiachen, et al.
Published: (2023)

What Foundation Models can Bring for Robot Learning in Manipulation : A Survey
by: Li, Dingzhe, et al.
Published: (2024)

Dynamic Policy Learning for Legged Robot with Simplified Model Pretraining and Model Homotopy Transfer
by: Kang, Dongyun, et al.
Published: (2025)

Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
by: Zhu, Chuning, et al.
Published: (2025)

DexSim2Real: Foundation Model-Guided Sim-to-Real Transfer for Generalizable Dexterous Manipulation
by: Zeng, Zijian, et al.
Published: (2026)

RoTri-Diff: A Spatial Robot-Object Triadic Interaction-Guided Diffusion Model for Bimanual Manipulation
by: Chen, Zixuan, et al.
Published: (2026)

RISE: Self-Improving Robot Policy with Compositional World Model
by: Yang, Jiazhi, et al.
Published: (2026)

Building Explicit World Model for Zero-Shot Open-World Object Manipulation
by: Li, Xiaotong, et al.
Published: (2026)

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
by: Li, Can, et al.
Published: (2026)