Author

Hongzhou Wang

h-index 0 View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

RE-0: Verified Recursive Improvement of Embodied Code-as-Policy Agents through Local On-Policy Distillation

RE-0, a recursively verified policy improvement framework, which improves both teacher-assisted execution and the standalone student, and generalizes to novel robots and scenes, and RE-OPD, which turns verified interventions into supervision for on-policy distillation.

Jia-Wei Zhang, Xiang-Rong Zhang, Rui-Ke Song et al. · 0 citations

Preprint Aug 2026

PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation

PACE, a credit-assignment framework for post-training on long-horizon manipulation, centered on a phase-progress-aware critic, is presented, demonstrating that PACE consistently achieves significant improvements over the strongest baseline.

Cheng-Ye Song, Jia-Wei Zhang, Rui-Ke Song et al. · 1 citation