hugpadhugpad

sensenova / sensenova-roborsi-27b-preview

Agents27B23410Updated Oct 23, 2026
Hugging Face

Downloads

234

Likes

10

Last updated

Oct 23, 2026

License

apache-2.0

SenseNova-RoboRSI-27B-Preview is an open-weight 27B vision-language model for embodied agents. Through joint model–Harness RSI, it learns from validated interaction experience, developing capabilities for planning, action decisions, and feedback-based correction in simulation …

Tasks & library

  • robotics

Tags

  • qwen3_5
  • vision-language-model
  • embodied-ai
  • robotics
  • agent
  • recursive-self-improvement

Technical specifications

Parameters27B
LibraryNot available
LanguagesNot available
Base modelQwen/Qwen3.8-27B
Licenseapache-2.0