Author

Miao-Wen Wen

h-index 55 View on Semantic Scholar

We have 1 of 435 papers

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.

Preprint Aug 2026

When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO

Cue-GRPO improves AIME repeated-sampling performance and introduces a partition- conditioned rule that redistributes positive advantages accord- ing to cluster rarity, with Strategy Cues providing a low-overhead implementation for competition mathematics.

Zhenzhen Cao, Miao-Wen Wen, Fangjiong Chen · 0 citations