Skip to content
HuggingFace Daily Papers·· 22 days agoAI score60

RoboCasa-Shift: A Stage-Aware Robustness Benchmark for VLA Policies in Long-Horizon Household Manipulation

Summary

The paper introduces RoboCasa-Shift, a diagnostic robustness benchmark built on RoboCasa365 for evaluating how vision-language-action (VLA) policies handle distribution shifts in long-horizon household manipulation tasks.

This page provides a summary and source link only. Read the full article at the source.

Source: HuggingFace Daily Papers · huggingface.co