Authors

Sixu Lin

Publications 2

Preprint Open access

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

Ruiyan Xu, Haisheng Su, Sixu Lin et al. · 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 …

Preprint Open access

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

Yunpeng Qing, Yilun Kong, Sixu Lin et al. · 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 …

Co-authors

Ruiyan Xu Haisheng Su Zhaokun Yue Chengming Hu Xin Jin Guiliang Liu Yunpeng Qing Yilun Kong Ming Zhou Yiming Fei Shuang Luo Yixiao Chi