Skip to content
conftrace_

approximate memorization

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

weight magnitude (1) attention-only transformer (1) memorization capacity (1) neural network (1) multi-head attention (1) language model (1) relu activation (1)

Papers

Memorization in Attention-only Transformers AISTATS 2025 Network size and size of the weights in memorization with two-layers neural networks NeurIPS 2020