b:botstest.Submit a resource ↗

Benchmarks / Research

Video2World · AetherLabsAI

Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective

policy evaluation
Publisher repository ↗
Video2World · AetherLabsAI resource page screenshot
Resource screenshot · captured 2026-10-10 · visually reviewed

Overview

Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective

Compare tasks, protocols, dataset/environment versions and hardware before interpreting reported results. A benchmark repository is not a certification of a robot system.

Project information

Maintainer
AetherLabsAI
Primary language
Python
Repository code license
Apache-2.0
Model-weight license
Not recorded
Dataset license
Not recorded
Hardware design license
Not recorded
Maintenance
Not archived in the last recorded metadata
Last observed repository push
2026-10-06

Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.

Documentation sections

  • Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
  • Overview
  • Installation
  • ManiSkill / SAPIEN: FurnitureBench, DROID, hand, Push-T
  • MuJoCo: rope routing, toy packing, cloth (a separate environment)
  • Isaac Sim 5.1 + Isaac Lab: RoboDojo and in-house (with a RoboDojo checkout at commit 25691aa)

Browse this resource’s categories

Explore related collections

Browse Benchmarks →