← Search

Shihao Hou

2 accepted papers

2026

Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

CVPR 2026

Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence of non-IID data and long-tailed class distributions, presenting unique challenges

Cited by 0SourcecodeScholar
2025

Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster

NeurIPS 2025poster

The success of the machine learning field has reliably depended on training on large datasets. While effective, this trend comes at an extraordinary cost. This is due to two deeply intertwined factors: the size of models and the size of datasets. While promising research efforts focus on reducing th…

Cited by 0SourcecodeScholar