https://github.com/2toinf/X-VLA

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"
https://github.com/2toinf/X-VLA

cloth-folding florence-2 manipulation pretrained-models robotics robotics-dataset vision-language-action-model vision-language-model

Last synced: 2 days ago
JSON representation

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

• Host: GitHub
• URL: https://github.com/2toinf/X-VLA
• Owner: 2toinf
• License: apache-2.0
• Created: 2025-09-25T07:49:18.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2026-03-09T13:30:04.000Z (3 months ago)
• Last Synced: 2026-03-09T18:10:46.778Z (3 months ago)
• Topics: cloth-folding, florence-2, manipulation, pretrained-models, robotics, robotics-dataset, vision-language-action-model, vision-language-model
• Language: C++
• Homepage: https://thu-air-dream.github.io/X-VLA/
• Size: 56.5 MB
• Stars: 544
• Watchers: 2
• Forks: 43
• Open Issues: 21
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-robotics-ee-opensource - GitHub