activity
20242026
collaborators

10 papers

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.LG2026

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…

cs.CV2026

Deep Clustering with Associative Memories

Bishwajit Saha, Dmitry Krotov, Mohammed J. Zaki +1

Deep clustering - joint representation learning and latent space clustering - is a well studied problem especially in computer vision and text processing under the deep learning fr…

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

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

Learning interpretable positional encodings in transformers depends on initialization

Takuya Ito, Luca Cocchi, Tim Klinger +3

In transformers, the positional encoding (PE) provides essential information that distinguishes the position and order amongst tokens in a sequence. Most prior investigations of PE…