Author

Sai Li

h-index 2 View on Semantic Scholar

We have 2 of 8 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 Jun 2026

Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models

Experiments on WMDP and MUSE-BOOKS across multiple MoE LLMs show that TRACE consistently improves the forget-utility trade-off, yielding a 9\% relative utility improvement over the strongest baseline under comparable forgetting quality and the best performance on three out of four MUSE-BOOKS metrics.

Jingyi Xie, Yi-Jun Lin, Yi Xiong et al. · arXiv.org · 0 citations

Jul 2026

Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation

This work proposes Context-Constrained Transfer Learning via ANchoring and DIstillation (TL-ANDI), a posterior-aware distillation framework for TFMs that constructs a compact source context by solving a budget-constrained optimal transport problem whose cost jointly measures target covariate coverage and posterior comp...

Yijun Lin, Sai Li · arXiv.org · 1 citation