Author

Hao-Wei Wang

h-index 11 View on Semantic Scholar

We have 1 of 25 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.

#artificial intelligence Preprint Aug 2026

ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration

ReNFT is proposed, which repairs a high-reward, low-diversity adapter through internal probability-mass recalibration through internal probability-mass recalibration, offering a complementary alternative to external interventions.

Yu-Chen Bao, Chao Wen, Haowei Wang et al. · 0 citations