Robuta

https://openreview.net/forum?id=ZCrRCICOkr OutEffHop: A Principled Outlier-Efficient Attention Layer from Dense Associative Memory Models |... We introduce a principled approach to Outlier-Efficient Attention Layers via associative memory models to reduce outlier emergence in large transformer-based... dense associative memory https://openreview.net/forum?id=kxnh3djvGg Dense Associative Memory for Gaussian Distributions | OpenReview Dense associative memories (DAMs) store and retrieve patterns via energy-function based fixed points, but existing models are limited to vector... dense associative memorygaussian distributionsopenreview https://openreview.net/forum?id=d7PjRsguov Energy Minimization for Training Dense Associative Memory | OpenReview Dense Associative Memories (DenseAMs) are modern generalizations of Hopfield networks with high-capacity, energy-based retrieval dynamics, but it remains... dense associative memoryenergy minimizationfor trainingopenreview