Learning to Learn with Contrastive Meta-Objective

NeurIPSOral2025

Authors
Shiguang Wu, Yaqing Wang, Yatao Bian, Quanming Yao
Affiliation
Tsinghua University, Tsinghua University
Venue
NeurIPS 2025
Track
Oral

TL;DR

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

meta-learning contrastive

← All NeurIPS 2025 Oral papers · Browse the whole archive