← Search

Yuxiang Luo

2 accepted papers

2026

TuneAhead: Predicting Fine-tuning Performance Before Training Begins

ICML 2026poster

Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance depends sensitively on data quality and hyperparameter choices, and naïve runs can even degrade model performance. This raises a fundamental question: Can we predict fine-tuning performance before traini…

Cited by 0SourceScholar