Meta Learning

OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav

We present a single neural network architecture composed of task-agnostic components (ViTs, convolutions, and LSTMs) that achieves state-of-art results on both the ImageNav and ObjectNav without task-specific modules.

La-MAML: Look-Ahead Meta-Learning for Continual Learning

In this work we develop a gradient-based meta-learning algorithm for efficient, online continual learning, that is robust and scalable to real-world visual benchmarks.