ResearchBenchmarksPreference-Aligned Reinforcement Learning on Fold ClothFollow1,790Label MetricPrefVLM84.4527.29701,412.8Jul 2, 2026Evaluation ResultsMethodMethodLinksLabel MetricImage MetricPrefVLM2026.071,79010,740ERL-VLM2026.07750750RL-VLM-F2026.075001,000CoRe2026.071501,200