Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

CVPR

Summary

Evo-1 studies how to keep semantic alignment strong while making vision-language-action models lighter and more practical for embodied tasks.

My Contributions

  • Supported simulation data processing
  • Adapted the model and benchmark environments
  • Ran most of the simulation experiments
  • Participated in result organization and analysis

Status

This work has been accepted by CVPR.