Author

Ze-Yu Dong

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.

#machine learning Preprint Sep 2026

Rethinking Class Imbalance for Single-Cell Foundation Models: A Systematic Benchmark Across Architectures and Long-Tail Loss Functions

This work presents a systematic benchmark of six long-tail loss functions (cross-entropy, weighted CE, class-balanced loss, focal loss, LDAM, logit-adjusted softmax), giving both a reusable benchmark and mechanism-grounded practical guidelines for combining foundation models with imbalanced biological data.

Ze-Yu Dong, Jia-Hui Zhong · 0 citations

#artificial intelligence Preprint Sep 2026

Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for Reliable Clinical LLM Answer Selection

ALTAS is introduced, which reads terminal entropy and late-layer linearity from one forward pass to choose per question between greedy decoding and late-layer trajectory correction and improves TruthfulQA over greedy at 3B and 8B.

Ze-Yu Dong, Benjamin Wang, Joyee W. Jin · 0 citations