Readings

Motivation

On the Measure of Intelligence Arxiv2019

A Path Towards Autonomous Machine Intelligence Arxiv2022

Basics of Meta-learning: Metric/Model/Optimisation-based

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks ICML2017

Conditional Neural Processes ICML2018

Matching Networks for One Shot Learning NeurIPS2016

Thinking Like Transformers NeurIPS2021

Transformers learn in-context by gradient descent ICLR2023

Meta Reinforcement Learning & Imitation Learning

A Survey of Meta-Reinforcement Learning Arxiv2023

RL2- Fast Reinforcement Learning via Slow Reinforcement Learning ICLR2017

Decision Transformer: Reinforcement Learning via Sequence Modeling NeurIPS2021

In-context Reinforcement Learning with Algorithm Distillation NeurIPS2022

Generative Models

Training Language Models to follow Instructions with Human feedback NeurIPS2022

Few-shot Classification of Tabular Data with Large Language Models Arxiv2022

Meta-Learning Fast Weight Language Models Arxiv2022

Meta-learning via Language Model In-context Tuning ACL2022

Online & Continual Learning

Winnowing with Gradient Descent PMLR2020

Gated Linear Networks AAAI2021

The Forward-Forward Algorithm NeurIPS2022

What’s Hidden in a Randomly Weighted Neural Network? CVPR2020

Supermasks in Superposition NeurIPS2020

Neuro-evolutionary Learning

Meta-Learning through Hebbian Plasticity in Random Networks NeurIPS2020

Augmenting Supervised Learning by Meta-learning Unsupervised Local Rules NeurIPS2019

Diffusion Models

Planning with Diffusion for Flexible Behavior Synthesis ICML2022

Note: while covering each paper we may need to also cover some key references therein; these are not listed above.