Article

Execution logs sway VLM judgments of robot progress

The study tested how text placed beside frames affects vision-language models judging robot videos: when a line saying "making progress" was added to clips where the robot was falling behind, Gemini, Qwen, and GPT judges flipped correct verdicts to "progress" 10 to 35 percentage points more often than with neutral text.

Part of the event: Execution logs can sway VLM judgments of robot progress

This page provides a summary and source link only.