Skip to content

Conversation

@atheendre130505
Copy link

  • Handle both 2-coordinate points [x,y] and 4-coordinate boxes [x1,y1,x2,y2]
  • Convert 2-coordinate points to small bounding boxes around the point
  • Add validation to skip invalid coordinate formats with warnings
  • Fix IndexError: list index out of range when model outputs 2 coordinates
  • Maintain backward compatibility with existing 4-coordinate functionality

Resolves grounding coordinate parsing issues in GUI agent tasks

- Handle both 2-coordinate points [x,y] and 4-coordinate boxes [x1,y1,x2,y2]
- Convert 2-coordinate points to small bounding boxes around the point
- Add validation to skip invalid coordinate formats with warnings
- Fix IndexError: list index out of range when model outputs 2 coordinates
- Maintain backward compatibility with existing 4-coordinate functionality

Resolves grounding coordinate parsing issues in GUI agent tasks
@atheendre130505 atheendre130505 marked this pull request as draft November 4, 2025 04:34
@atheendre130505 atheendre130505 marked this pull request as ready for review November 4, 2025 04:34
@atheendre130505
Copy link
Author

@aisensiy @truebit @shotarok @Sleepychord , please review the PR

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant