activity
20242026
most citedDense Associative Memory Through the Lens of Random Features

1 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers

Takuya Ito, Ruchir Puri, Murray Campbell +1

Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and length generalization benchmarks.…

cs.LG2026

What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching

Alec Helbling, Sebastian Gutierrez Hernandez, Benjamin Hoover +2

Recent work has shown that models flow matching models can be trained without explicit time conditioning, challenging the standard view that the interpolation time is needed to dis…

cs.LG2025

Modern Methods in Associative Memory

Dmitry Krotov, Benjamin Hoover, Parikshit Ram +1

Associative Memories like the famous Hopfield Networks are elegant models for describing fully recurrent neural networks whose fundamental job is to store and retrieve information.…

cs.LG2025

Transformers Learn Faster with Semantic Focus

Parikshit Ram, Kenneth L. Clarkson, Tim Klinger +2

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformer…

cs.LG2025

Transformer Circuits Can Realize Clustering Algorithms

Kenneth L. Clarkson, Lior Horesh, Takuya Ito +2

Although transformers are most commonly optimized as statistical sequence models, it is unclear to what extent they can implement and learn exact algorithmic computations. Here, we…

cs.LG2025

Dense Associative Memory with Epanechnikov Energy

Benjamin Hoover, Zhaoyang Shi, Krishnakumar Balasubramanian +2

We propose a novel energy function for Dense Associative Memory (DenseAM) networks, the log-sum-ReLU (LSR), inspired by optimal kernel density estimation. Unlike the common log-sum…