What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study
暂无中文版，显示英文原文。
摘自论文摘要
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.
摘自论文摘要，摘要生成中。
受许可协议限制，本站不转载该论文全文，仅提供摘要和原文链接。