RESEARCH PAPERYear 2026

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

Zijian Song; Qichang Li; Sihan Qin; Yuhao Chen; Tianshui Chen; Liang Lin; Guangrun Wang

Read paper PDF DOI

Classification

View four quadrants

Major category: WAMs
Quadrant: Q2 · One Model × IDM
Architecture: One Model
Prediction paradigm: IDM
Subcategories: Visual planning & IDM Efficient inference & real-time control
Source review status: Verified from primary sources

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@inproceedings{physgen,
  title={Learning physics from pretrained video models: A multimodal continuous and sequential world interaction models for robotic manipulation},
  author={Song, Zijian and Li, Qichang and Qin, Sihan and Chen, Yuhao and Chen, Tianshui and Lin, Liang and Wang, Guangrun},
  booktitle={ICMR},
  pages={758--767},
  year={2026}
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation

Grounding Generated Video Plans in Simulation Towards Versatile Dexterous Controllers

HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy