Author

Qipeng Zhan

View on Semantic Scholar

1 paper 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.

Preprint Aug 2026

Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration

Invertible Logits Transformation (InvLT), which applies a learned scalar MLP element-wise to the pre-softmax logits, consistently outperforms a broad set of post-hoc baselines on standard calibration metrics.

Lening Zhao, Qipeng Zhan, Li Shen · 0 citations