Prehistory — From Neural Networks to the TransformerChelsea Finn, Pieter Abbeel, Sergey Levine (UC Berkeley)UC Berkeley

Finn, Abbeel and Levine publish Model-Agnostic Meta-Learning (MAML) on arXiv

Model-Agnostic Meta-Learning (MAML) released on arXiv

Why it matters

Proposed architecture-agnostic meta-learning, opening up research on few-shot adaptation

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1703.03400

Added in Week 35, 2026 · See that week

Same week

Google releases XLAOfficial

Nearby on the same axis

Zhu et al. publish CycleGAN on arXivPaperIn-Datacenter Performance Analysis of a Tensor Processing UnitPaperArjovsky, Chintala and Bottou publish Wasserstein GAN on arXivPaperConvolutional Sequence to Sequence Learning (ConvS2S) released on arXivPaper