OSعُمان للعلوم
الباحثون

Sixu Lin

المنشورات 2

نسخة أولية وصول مفتوح

$R^2$-WAM: Repair-and-Reject Post-Training for World Action Models

Ruiyan Xu, Haisheng Su, Sixu Lin وآخرون · 2026

World Action Models (WAMs) emerge as a promising foundation for policy refinement by predicting the consequences of sampled actions. However, visually plausible predictions can mislead policy refinement if they fail to reflect the input actions. To address this mismatch, we introduce $R^2$-WAM, a two-stage repair-and-r …

نسخة أولية وصول مفتوح

PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models

Yunpeng Qing, Yilun Kong, Sixu Lin وآخرون · 2026

Reinforcement Fine-Tuning~(RFT) has emerged as a promising paradigm for improving Vision-Language-Action~(VLA) policies, yet sparse task-level outcomes provide limited credit for intermediate transitions, especially in long-horizon manipulation. A natural approach is to model intermediate task progress and use it as de …

المؤلفون المشاركون

Ruiyan XuHaisheng SuZhaokun YueChengming HuXin JinGuiliang LiuYunpeng QingYilun KongMing ZhouYiming FeiShuang LuoYixiao Chi