# worv-ai/d2e

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/worv-ai-d2e).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

87 stars · 2 forks · Python

## Links

- GitHub: https://github.com/worv-ai/D2E
- Homepage: https://worv-ai.github.io/d2e/
- awesome-repositories: https://awesome-repositories.com/repository/worv-ai-d2e.md

## Description

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

## Tags

### Part of an Awesome List

- [Embodied Foundation Models](https://awesome-repositories.com/f/awesome-lists/ai/embodied-foundation-models.md) — Scaling pretraining on desktop data for embodied transfer.
- [Manipulation and Control](https://awesome-repositories.com/f/awesome-lists/ai/manipulation-and-control.md) — Scaling vision-action pretraining for embodied AI.