Abstract We introduce Meta-AdaM, a meta-learned adaptive optimizer with momentum,
designed for few-shot learning tasks that pose significant challenges to deep learning …

Bi-level optimization, especially the gradient-based category, has been widely used in the
deep learning community including hyperparameter optimization and meta-knowledge …

Meta-learning is one of the important methods to solve the challenging few-shot learning
setting by using previous knowledge and experience to guide the learning of new tasks …

Learning with few labeled tabular samples is often an essential requirement for industrial
machine learning applications as varieties of tabular data suffer from high annotation costs …

We introduce an efficient optimization-based meta-learning technique for large-scale neural
field training by realizing significant memory savings through automated online context point …

Despite its practical importance across a wide range of modalities, recent advances in self-
supervised learning (SSL) have been primarily focused on a few well-curated domains, eg …

Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple
pre-trained models without requiring their original training data. Existing inversion-based …

Zero-shot coordination problem in multi-agent reinforcement learning (MARL), which
requires agents to adapt to unseen agents, has attracted increasing attention. Traditional …

Abstract Recently,(coordinate-based) sinusoidal neural networks have exhibited promising
results in representing most signals in computer graphics, such as images and implicit …