RESEARCH PAPERYear 2026

Interactive World Simulator for Robot Policy Training and Evaluation

Yixuan Wang; Rhythm Syed; Fangyu Wu; Mengchao Zhang; Aykut Onol; Jose Barreiros; Hooshang Nayyeri; Tony Dear; Huan Zhang; Yunzhu Li

Read on arXiv PDF Project page

Classification

View four quadrants

Major category: Benchmarks & simulators
Quadrant: Not applicable
Architecture: Not applicable
Prediction paradigm: Not applicable
Subcategories: Neural world simulators Evaluation metrics & protocols
Source review status: Verified from primary sources

Category review. Interactive World Simulator learns action-conditioned visual dynamics and exposes generated observations for human demonstration collection or separate-policy evaluation. Controls remain external and it predicts next-frame latents/RGB rather than selecting actions. Its natural home is neural simulation. 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

@inproceedings{
iws,
title={Interactive World Simulator for Robot Policy Training and Evaluation},
author={Yixuan Wang and Rhythm Syed and Fangyu Wu and Mengchao Zhang and Aykut Onol and Jose Barreiros and Hooshang Nayyeri and Tony Dear and Huan Zhang and Yunzhu Li},
booktitle={RSS Workshop},
year={2026},
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

Programmable World Model

FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects

TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image