Yanlai Yang — accepted AI-conference papers

2024

Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training

Yanlai Yang, Matt Jones, Michael Curtis Mozer, Mengye Ren

NeurIPS 2024poster

We explore the training dynamics of neural networks in a structured non-IID setting where documents are presented cyclically in a fixed, repeated sequence. Typically, networks suffer from catastrophic interference when training on a sequence of documents; however, we discover a curious and remarkabl…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials

Aviral Kumar, Anikait Singh, Frederik D Ebert, Mitsuhiko Nakamoto, Yanlai Yang, Chelsea Finn +1

RSS 2023poster

Progress in deep learning highlights the tremendous potential of utilizing diverse datasets for attaining effective generalization and makes it enticing to consider leveraging broad datasets for attaining robust generalization in robotic learning as well. However, in practice we often want to learn…

Cited by 80 Source ↗PDF ↗Scholar ↗