How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
RynnVLA-002: A Unified Vision-Language-Action and World Model
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI [ICLR 2026]
The main features of worv-ai/d2e are: Embodied Foundation Models, Manipulation and Control.
Open-source alternatives to worv-ai/d2e include: ahundt/robotsenactmalignantstereotypes. alibaba-damo-academy/worldvla — RynnVLA-002: A Unified Vision-Language-Action and World Model. allenai/embodied-clip. amap-cvlab/abot-manipulation — ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning. arashakb/actquant — Official implementation of ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models. agibottech/genie-envisioner — Join our WeChat Group.
