What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study
How should demonstration quality be used during vision-language-action (VLA) pretraining to improve performance after target-task fine-tuning? We compare weighting, filtering, and conditioning across reward definitions and label granularities using 5,000 naturally suboptimal human demonstrations and 24 target tasks. Within each VLA, we match demonstrations and training budgets. Additional…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
