b:botstest.Submit a resource ↗

Software / Research

D2E · worv-ai

Vision-action pretraining on desktop data for transfer to embodied AI.

Publisher repository ↗
D2E · worv-ai resource page screenshot
Resource screenshot · captured 2026-10-08 · visually reviewed

Overview

Vision-action pretraining on desktop data for transfer to embodied AI.

Publisher summary: “D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI [ICLR 2026]”

Use its repository to inspect the implementation, documentation and supported workflows. This directory record identifies the maintainer, code license and related resources; it does not claim that the project has been installed or tested on your robot.

Project information

Maintainer
worv-ai
Primary language
Python
Repository code license
Not specified
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
2026-07-16

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

Documentation sections

  • D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
  • News
  • Dataset
  • What's Included
  • Quick Start
  • Download a sample recording (mcap + video)

Browse this resource’s categories

Software / Perception & geometry ↗

Explore related collections

Browse Software →

More in Software