Min Cao

M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios

2023 · arXiv (Cornell University)

In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown classes (i.e., not seen during training), they always predict …

Progressive Depth Up-scaling via Optimal Transport

2025 · arXiv (Cornell University)

Scaling Large Language Models (LLMs) yields performance gains but incurs substantial training costs. Depth up-scaling offers training efficiency by adding new layers to pre-trained models. However, most existing methods copy or average weights from base …