activity
20192026
most citedAn Algorithm for Routing Vectors in Sequences

9 citations · 14 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2026

Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation

Franz A. Heinsen, Leo Kozachkov

The most widely used artificial intelligence (AI) models today are Transformers employing self-attention. In its standard form, self-attention incurs costs that increase with conte…

cs.LG2025

Generalized Orders of Magnitude for Scalable, Parallel, High-Dynamic-Range Computation

Franz A. Heinsen, Leo Kozachkov

Many domains, from deep learning to finance, require compounding real numbers over long sequences, often leading to catastrophic numerical underflow or overflow. We introduce gener…

cs.LG2024

Softmax Attention with Constant Cost per Token

Franz A. Heinsen

We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we…

cs.DS2023

Efficient Parallelization of a Ubiquitous Sequential Computation

Franz A. Heinsen

We find a succinct expression for computing the sequence in parallel with two prefix sums, given , , $b_t \in…

cs.LG2022★ 9 cited

An Algorithm for Routing Vectors in Sequences

Franz A. Heinsen

We propose a routing algorithm that takes a sequence of vectors and computes a new sequence with specified length and vector size. Each output vector maximizes "bang per bit," the…

cs.LG2022

Tree Methods for Hierarchical Classification in Parallel

Franz A. Heinsen

We propose methods that enable efficient hierarchical classification in parallel. Our methods transform a batch of classification scores and labels, corresponding to given nodes in…