Fine-Tuning in Modern Machine Learning: Principles and Scalability (FITML)

NeurIPS 2024 Workshop

More information on Googlesites webpage

Call for paper


This FITML workshop aims to contribute to the recent radical paradigm shift for fine-tuning in modern machine learning, theoretically, computationally, and systematically. It encourages researchers to push forward the frontiers of theoretical understanding of fine-tuning, devising expeditious and resource-efficient inference and fine-tuning methods in machine learning systems, enabling their deployment within constrained computational resources. This FITML workshop explores theoretical and/or empirical results for understanding and advancing modern practices for efficiency in machine learning.

Important information


Invited speakers


Panel members


The FITML Organizers


Fanghui Liu (Warwick), Grigorios Chrysos (UW-Madison), Beidi Chen (CMU), Rebekka Burkholz (CISPA), Saleh Soltan (Amazon), Angeliki Giannou (UW-Madison), Masashi Sugiyama (UTokyo/RIKEN), Volkan Cevher (EPFL)

The FITML Volunteers


Yongtao Wu (EPFL), Yuanhe Zhang (Warwick)

Contact

preferred contact email: neurips24fitml@outlook.com or contact Fanghui.

© This webpage was in part inspired from this template.