English

MT2ST: Adaptive Multi-Task to Single-Task Learning

Machine Learning 2025-05-02 v6

Abstract

Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in multi-task learning (MTL) and precision in single-task learning (STL) by introducing the Multi-Task to Single-Task (MT2ST) framework. MT2ST is designed to enhance training efficiency and accuracy in multi-modal tasks, showcasing its value as a practical application of efficient ML.

Keywords

Cite

@article{arxiv.2406.18038,
  title  = {MT2ST: Adaptive Multi-Task to Single-Task Learning},
  author = {Dong Liu and Yanxuan Yu},
  journal= {arXiv preprint arXiv:2406.18038},
  year   = {2025}
}
R2 v1 2026-06-28T17:19:24.910Z