RESEARCH PAPERYear 2026

DreamDojo: A Real-Time Robot World Model from Large-Scale Human Videos

View all authors

Shenyuan Gao; William Liang; Kaiyuan Zheng; Ayaan Malik; Seonghyeon Ye; Sihyun Yu; Wei-Cheng Tseng; Yuzhu Dong; Kaichun Mo; Chen-Hsuan Lin; Qianli Ma; Seungjun Nah; Loic Magne; Jiannan Xiang; Yuqi Xie; Ruijie Zheng; Dantong Niu; You Liang Tan; K. R. Zentner; George Kurian; Suneel Indupuru; Pooya Jannaty; Jinwei Gu; Jun Zhang; Jitendra Malik; Pieter Abbeel; Ming-Yu Liu; Yuke Zhu; Joel Jang; Linxi "Jim" Fan

Classification

View four quadrants
Major category
WAMs
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. DreamDojo adapts a video foundation model to action-conditioned robot dynamics, and a separate policy/value pipeline uses its predicted candidate futures for planning. This is a task-specific world-model-and-control system, not the Cosmos or WAN component it builds upon. Reading evidence

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