Shiao Xie
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1
Frequent co-authors
Research Timeline
2026
Reinforcement Learning with Visually Attributable On-Policy Self-Distillation
This paper proposes a new approach to multimodal reinforcement learning with verifiable rewards that preserves visually grounded guidance while suppressing inconsistent corrections.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIEmpiricalRecentOct 19, 2026
Reinforcement Learning with Visually Attributable On-Policy Self-Distillation
Shiao Xie, Siyu Chen, Jianwei Lv, Xiandong Li +1 more
This paper proposes a new approach to multimodal reinforcement learning with verifiable rewards that preserves visually grounded guidance while suppressing inconsistent corrections.
View →