3 papers
stat.ML2026
Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation
Yijun Lin, Sai Li
Tabular Foundation Models (TFMs) have demonstrated strong empirical performance as black-box inference engines through in-context learning. However, their use in transfer learning…
cs.CL2026
Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models
Jingyi Xie, Yijun Lin, Yinjiang Xiong +2
Machine unlearning is increasingly important for large language models, yet unlearning in Mixture-of-Experts (MoE) architectures remains underexplored. Unlike dense models, MoE arc…
cs.CL2026
SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
Yijun Lin, Jinhao Sheng, Qingyue Cai +1
Autoregressive language models suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by employing a lightweight draft…